|
21798
|
whisper_init_state: kv pad size = 2.36 MB
whi whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:33:55.437876Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:35:57.413206Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
2026-05-11T22:37:14.870936Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=1.714129166s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:37:59.603705Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:40:02.174925Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/.screenpipe $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-12T09:21:07.201625Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-12T09:21:07.328817Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-12T09:21:10.020463Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-12T09:21:10.024711Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-12T09:21:10.025571Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-12T09:21:10.055207Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-12T09:21:10.055275Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-12T09:21:10.666779Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-12T09:21:10.666832Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-12T09:21:10.666681Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-12T09:21:10.666983Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-12T09:21:10.666647Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-12T09:21:10.673969Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-12T09:21:10.675449Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-12T09:21:10.676236Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-12T09:21:10.676638Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-12T09:21:10.677056Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-12T09:21:10.677293Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-12T09:21:10.677398Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ MacBook Pro Microphone (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-12T09:21:10.684547Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
2026-05-12T09:21:10.686111Z INFO screenpipe: starting UI event capture
2026-05-12T09:21:10.696691Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-12T09:21:10.705742Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-12T09:21:10.712331Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-12T09:21:10.753596Z INFO screenpipe_engine::ui_recorder: UI recording session started: eee53fe6-52d6-4c4e-a7e5-11ede410f444
2026-05-12T09:21:10.753638Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-12T09:21:10.753679Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-11 06:21:10.753677 UTC to 2026-05-12 06:21:10.753677 UTC)
2026-05-12T09:21:10.754945Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-12T09:21:10.764596Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-12T09:21:10.771437Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-12T09:21:15.451981Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=6633 elapsed=4.697616625s
2026-05-12T09:21:15.476188Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 6633 frame entries, coverage from 2026-05-11 06:21:10.753677 UTC
2026-05-12T09:21:16.549935Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-12T09:21:16.550139Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-12T09:21:16.550184Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-12T09:21:19.459497Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-12T09:21:19.463986Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-12T09:21:19.465573Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-12T09:21:19.467110Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-12T09:21:19.468420Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-12T09:21:20.691544Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-12T09:21:20.692520Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-12T09:21:20.692565Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.036 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-12T09:21:20.866406Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-12T09:21:20.896976Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-12T09:21:20.928794Z INFO screenpipe_audio::audio_manager::manager: seeded 14 speakers (named + unnamed) from DB into embedding manager
2026-05-12T09:21:20.929372Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-12T09:21:20.930136Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-12T09:21:21.212480Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-12T09:21:22.112224Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-12T09:21:22.697027Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=21773, dur=116ms
2026-05-12T09:21:23.853614Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-12T09:21:23.854499Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-12T09:21:23.854491Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-12T09:21:28.046940Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-12T09:21:28.381213Z WARN screenpipe_a11y::tree::macos_lines: lines: AXUIElementCopyParameterizedAttributeValue(AXLineForIndex) failed status=os::Status { raw: -25212, fcc: "....", help: "https://www.osstatus.com?search=-25212" } — first failure (further failures suppressed); search highlights will fall back to paragraph bbox on this app
2026-05-12T09:21:28.684461Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=21775, dur=90ms
2026-05-12T09:22:12.427026Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=2 elapsed=1.759127041s
2026-05-12T09:22:12.427274Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 2 eligible frames
2026-05-12T09:22:12.869213Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 1 frames, 0.2MB → 0.3MB (0.9x), 1 JPEGs deleted
2026-05-12T09:22:13.304558Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 1 frames, 0.3MB → 0.4MB (0.9x), 1 JPEGs deleted
2026-05-12T09:22:39.009649Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1944753676112650055, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency...
|
iTerm2
|
screenpipe"
|
NULL
|
21798
|
|
21799
|
whisper_init_state: kv pad size = 2.36 MB
whi whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:33:55.437876Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:35:57.413206Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
2026-05-11T22:37:14.870936Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=0 elapsed=1.714129166s
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:37:59.603705Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:40:02.174925Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: install a starter bundle of pipes:
screenpipe install [URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/.screenpipe $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-12T09:21:07.201625Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-12T09:21:07.328817Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-12T09:21:10.020463Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-12T09:21:10.024711Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-12T09:21:10.025571Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-12T09:21:10.055207Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-12T09:21:10.055275Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-12T09:21:10.666779Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-12T09:21:10.666832Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-12T09:21:10.666681Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-12T09:21:10.666983Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-12T09:21:10.666647Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-12T09:21:10.673969Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-12T09:21:10.675449Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-12T09:21:10.676236Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-12T09:21:10.676638Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-12T09:21:10.677056Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-12T09:21:10.677293Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-12T09:21:10.677398Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ MacBook Pro Microphone (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-12T09:21:10.684547Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
2026-05-12T09:21:10.686111Z INFO screenpipe: starting UI event capture
2026-05-12T09:21:10.696691Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-12T09:21:10.705742Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-12T09:21:10.712331Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-12T09:21:10.753596Z INFO screenpipe_engine::ui_recorder: UI recording session started: eee53fe6-52d6-4c4e-a7e5-11ede410f444
2026-05-12T09:21:10.753638Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-12T09:21:10.753679Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-11 06:21:10.753677 UTC to 2026-05-12 06:21:10.753677 UTC)
2026-05-12T09:21:10.754945Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-12T09:21:10.764596Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-12T09:21:10.771437Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-12T09:21:15.451981Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=6633 elapsed=4.697616625s
2026-05-12T09:21:15.476188Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 6633 frame entries, coverage from 2026-05-11 06:21:10.753677 UTC
2026-05-12T09:21:16.549935Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-12T09:21:16.550139Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-12T09:21:16.550184Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-12T09:21:19.459497Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-12T09:21:19.463986Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-12T09:21:19.465573Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-12T09:21:19.467110Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-12T09:21:19.468420Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-12T09:21:20.691544Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-12T09:21:20.692520Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-12T09:21:20.692565Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.036 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-12T09:21:20.866406Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-12T09:21:20.896976Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-12T09:21:20.928794Z INFO screenpipe_audio::audio_manager::manager: seeded 14 speakers (named + unnamed) from DB into embedding manager
2026-05-12T09:21:20.929372Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-12T09:21:20.930136Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-12T09:21:21.212480Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-12T09:21:22.112224Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-12T09:21:22.697027Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=21773, dur=116ms
2026-05-12T09:21:23.853614Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-12T09:21:23.854499Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-12T09:21:23.854491Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-12T09:21:28.046940Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-12T09:21:28.381213Z WARN screenpipe_a11y::tree::macos_lines: lines: AXUIElementCopyParameterizedAttributeValue(AXLineForIndex) failed status=os::Status { raw: -25212, fcc: "....", help: "https://www.osstatus.com?search=-25212" } — first failure (further failures suppressed); search highlights will fall back to paragraph bbox on this app
2026-05-12T09:21:28.684461Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=21775, dur=90ms
2026-05-12T09:22:12.427026Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=2 elapsed=1.759127041s
2026-05-12T09:22:12.427274Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 2 eligible frames
2026-05-12T09:22:12.869213Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 1 frames, 0.2MB → 0.3MB (0.9x), 1 JPEGs deleted
2026-05-12T09:22:13.304558Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 1 frames, 0.3MB → 0.4MB (0.9x), 1 JPEGs deleted
2026-05-12T09:22:39.009649Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1944753676112650055, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency...
|
iTerm2
|
screenpipe"
|
NULL
|
21799
|
|
21820
|
ggml_metal_init: use fusion = true
ggml_me ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:44:07.738461Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:46:10.863483Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:48:13.767660Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-11T22:50:16.132089Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
[URL_WITH_CREDENTIALS] record
lukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/.screenpipe $ npx screenpipe@latest record
detected hardware tier: Mid
warning: parakeet is not supported on this platform, using whisper-tiny instead
2026-05-12T09:21:07.201625Z INFO screenpipe_engine::auth_key: api auth: key resolved via secret store
checking permissions...
screen recording: ok
microphone: ok
accessibility: ok
2026-05-12T09:21:07.328817Z INFO screenpipe_screen::monitor::macos_version: Detected macOS version: 14.6
2026-05-12T09:21:10.020463Z INFO screenpipe_engine::sleep_monitor: Starting macOS sleep/wake monitor
2026-05-12T09:21:10.024711Z INFO screenpipe_engine::sleep_monitor: Screen lock/unlock observers registered (CFNotificationCenter)
2026-05-12T09:21:10.025571Z INFO screenpipe_engine::sleep_monitor: Display reconfiguration watcher registered (CGDisplayRegisterReconfigurationCallback)
2026-05-12T09:21:10.055207Z INFO screenpipe_engine::permission_monitor: permission monitor started screen=true mic=true accessibility=true keychain=true
2026-05-12T09:21:10.055275Z INFO screenpipe: meeting detector enabled — independent of transcription mode
2026-05-12T09:21:10.666779Z INFO screenpipe: API server listening on [IP_ADDRESS]:3030 (localhost only)
2026-05-12T09:21:10.666832Z INFO screenpipe: API auth enabled — run `screenpipe auth token` to view your key
2026-05-12T09:21:10.666681Z INFO screenpipe_engine::power::manager: power manager started (poll interval: 10s)
2026-05-12T09:21:10.666983Z INFO screenpipe_engine::vision_manager::manager: Starting VisionManager
2026-05-12T09:21:10.666647Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction worker started (min_age=600s, poll=300s)
2026-05-12T09:21:10.673969Z INFO screenpipe_core::pipes: loaded pipe: day-recap
2026-05-12T09:21:10.675449Z INFO screenpipe_core::pipes: loaded pipe: standup-update
2026-05-12T09:21:10.676236Z INFO screenpipe_core::pipes: loaded pipe: ai-habits
2026-05-12T09:21:10.676638Z INFO screenpipe_core::pipes: loaded pipe: time-breakdown
2026-05-12T09:21:10.677056Z INFO screenpipe_core::pipes: loaded pipe: video-export
2026-05-12T09:21:10.677293Z INFO screenpipe_core::pipes: loaded pipe: meeting-summary
2026-05-12T09:21:10.677398Z INFO screenpipe_core::pipes: loaded 6 pipes from "/Users/lukas/.screenpipe/pipes"
_
__________________ ___ ____ ____ (_____ ___
/ ___/ ___/ ___/ _ \/ _ \/ __ \ / __ \/ / __ \/ _ \
(__ / /__/ / / __/ __/ / / / / /_/ / / /_/ / __/
/____/\___/_/ \___/\___/_/ /_/ / .___/_/ .___/\___/
/_/ /_/
power AI by everything you've seen, said or heard
open source | runs locally | developer friendly
┌────────────────────────┬────────────────────────────────────┐
│ setting │ value │
├────────────────────────┼────────────────────────────────────┤
│ audio chunk duration │ 30 seconds │
│ port │ 3030 │
│ audio disabled │ false │
│ vision disabled │ false │
│ pause on DRM content │ false │
│ audio engine │ Parakeet │
│ vad engine │ Silero │
│ data directory │ /Users/lukas/.screenpipe │
│ debug mode │ false │
│ telemetry │ true │
│ use pii removal │ true │
│ use all monitors │ true │
│ ignored windows │ [] │
│ included windows │ [] │
│ cloud sync │ disabled │
│ auto-destruct pid │ 0 │
│ deepgram key │ not set │
│ api auth │ enabled │
│ encrypt secrets │ disabled │
│ retention days │ 14 │
│ retention mode │ media-only (keep transcripts) │
├────────────────────────┼────────────────────────────────────┤
│ languages │ │
│ │ all languages │
├────────────────────────┼────────────────────────────────────┤
│ monitors │ │
│ │ id: 1 │
│ │ id: 2 │
├────────────────────────┼────────────────────────────────────┤
│ audio devices │ │
│ │ MacBook Pro Microphone (input) │
│ │ System Audio (output) │
└────────────────────────┴────────────────────────────────────┘
you are using local processing. all your data stays on your computer.
warning: telemetry is enabled. only error-level data will be sent.
to disable, use the --disable-telemetry flag.
check latest changes here: https://github.com/screenpipe/screenpipe/releases
2026-05-12T09:21:10.684547Z INFO screenpipe_core::pipes: pipe scheduler started (generation 2)
2026-05-12T09:21:10.686111Z INFO screenpipe: starting UI event capture
2026-05-12T09:21:10.696691Z WARN screenpipe: pi agent install failed: bun not found — install from https://bun.sh
2026-05-12T09:21:10.705742Z INFO screenpipe_engine::power::manager: initial power profile: Performance (on_ac=true, battery=Some(100))
2026-05-12T09:21:10.712331Z INFO screenpipe_engine::ui_recorder: Starting UI event capture
2026-05-12T09:21:10.753596Z INFO screenpipe_engine::ui_recorder: UI recording session started: eee53fe6-52d6-4c4e-a7e5-11ede410f444
2026-05-12T09:21:10.753638Z INFO screenpipe_engine::calendar_speaker_id: speaker identification: started (user_name=<not set>)
2026-05-12T09:21:10.753679Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warming from DB (2026-05-11 06:21:10.753677 UTC to 2026-05-12 06:21:10.753677 UTC)
2026-05-12T09:21:10.754945Z INFO screenpipe_engine::meeting_detector: meeting v2: detection loop started (base_interval=5s, profiles=12)
2026-05-12T09:21:10.764596Z INFO screenpipe_engine::server: Server listening on [IP_ADDRESS]:3030
2026-05-12T09:21:10.771437Z INFO screenpipe_connect::mdns: mdns: advertising screenpipe on port 3030
2026-05-12T09:21:15.451981Z WARN sqlx::query: summary="SELECT f.id, f.timestamp, f.offset_index, …" db.statement="\n\nSELECT\n f.id,\n f.timestamp,\n f.offset_index,\n COALESCE(\n SUBSTR(f.full_text, 1, 200),\n SUBSTR(f.accessibility_text, 1, 200),\n (\n SELECT\n SUBSTR(ot.text, 1, 200)\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as text,\n COALESCE(\n f.app_name,\n (\n SELECT\n ot.app_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as app_name,\n COALESCE(\n f.window_name,\n (\n SELECT\n ot.window_name\n FROM\n ocr_text ot\n WHERE\n ot.frame_id = f.id\n LIMIT\n 1\n )\n ) as window_name,\n COALESCE(vc.device_name, f.device_name) as screen_device,\n COALESCE(vc.file_path, f.snapshot_path) as video_path,\n COALESCE(vc.fps, 0.033) as chunk_fps,\n f.browser_url,\n f.machine_id\nFROM\n frames f\n LEFT JOIN video_chunks vc ON f.video_chunk_id = vc.id\nWHERE\n f.timestamp >= ?1\n AND f.timestamp <= ?2\n AND COALESCE(vc.file_path, f.snapshot_path, '') NOT LIKE 'cloud://%'\nORDER BY\n f.timestamp DESC,\n f.offset_index DESC\nLIMIT\n 10000\n" rows_affected=0 rows_returned=6633 elapsed=4.697616625s
2026-05-12T09:21:15.476188Z INFO screenpipe_engine::hot_frame_cache: hot_frame_cache: warmed with 6633 frame entries, coverage from 2026-05-11 06:21:10.753677 UTC
2026-05-12T09:21:16.549935Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 1 (1440x900)
2026-05-12T09:21:16.550139Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 1 (device: monitor_1)
2026-05-12T09:21:16.550184Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 1 (device: monitor_1)
2026-05-12T09:21:19.459497Z INFO screenpipe_engine::vision_manager::manager: Starting vision recording for monitor 2 (3008x1253)
2026-05-12T09:21:19.463986Z INFO screenpipe_engine::vision_manager::manager: Starting event-driven capture for monitor 2 (device: monitor_2)
2026-05-12T09:21:19.465573Z INFO screenpipe_engine::vision_manager::manager: VisionManager started with 2/2 monitor(s)
2026-05-12T09:21:19.467110Z INFO screenpipe_engine::vision_manager::monitor_watcher: Starting monitor watcher (event-driven via CGDisplayRegisterReconfigurationCallback, 60s backstop poll)
2026-05-12T09:21:19.468420Z INFO screenpipe_engine::event_driven_capture: event-driven capture started for monitor 2 (device: monitor_2)
2026-05-12T09:21:20.691544Z INFO screenpipe_audio::transcription::engine: whisper model available: "/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin"
2026-05-12T09:21:20.692520Z INFO screenpipe_audio::transcription::whisper::model: whisper context: gpu acceleration enabled (Metal on macOS, Vulkan on Windows)
2026-05-12T09:21:20.692565Z INFO screenpipe_audio::transcription::engine: loading whisper model with GPU acceleration...
whisper_init_from_file_with_params_no_state: loading model from '/Users/lukas/.cache/huggingface/hub/models--ggerganov--whisper.cpp/snapshots/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.036 sec
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name: Apple M1
ggml_metal_device_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: has tensor = false
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 11453.25 MB
whisper_init_with_params_no_state: devices = 3
whisper_init_with_params_no_state: backends = 3
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 384
whisper_model_load: n_audio_head = 6
whisper_model_load: n_audio_layer = 4
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 384
whisper_model_load: n_text_head = 6
whisper_model_load: n_text_layer = 4
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 1 (tiny)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: Metal total size = 77.11 MB
whisper_model_load: model size = 77.11 MB
2026-05-12T09:21:20.866406Z INFO screenpipe_audio::transcription::engine: whisper model loaded successfully
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-12T09:21:20.896976Z INFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)
2026-05-12T09:21:20.928794Z INFO screenpipe_audio::audio_manager::manager: seeded 14 speakers (named + unnamed) from DB into embedding manager
2026-05-12T09:21:20.929372Z INFO screenpipe_audio::audio_manager::manager: audio manager started
2026-05-12T09:21:20.930136Z INFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events
2026-05-12T09:21:21.212480Z INFO screenpipe_audio::device::device_manager: starting recording for device: MacBook Pro Microphone (input)
2026-05-12T09:21:22.112224Z INFO sck_rs::stream_manager: persistent SCK stream started for display 1 (1440x900, 2fps, 0 excluded)
2026-05-12T09:21:22.697027Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 1: frame_id=21773, dur=116ms
2026-05-12T09:21:23.853614Z INFO screenpipe_audio::device::device_manager: starting recording for device: System Audio (output)
2026-05-12T09:21:23.854499Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)
2026-05-12T09:21:23.854491Z INFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for MacBook Pro Microphone (input) (wired / 30s segments)
2026-05-12T09:21:28.046940Z INFO sck_rs::stream_manager: persistent SCK stream started for display 2 (3008x1253, 2fps, 0 excluded)
2026-05-12T09:21:28.381213Z WARN screenpipe_a11y::tree::macos_lines: lines: AXUIElementCopyParameterizedAttributeValue(AXLineForIndex) failed status=os::Status { raw: -25212, fcc: "....", help: "https://www.osstatus.com?search=-25212" } — first failure (further failures suppressed); search highlights will fall back to paragraph bbox on this app
2026-05-12T09:21:28.684461Z INFO screenpipe_engine::event_driven_capture: startup capture for monitor 2: frame_id=21775, dur=90ms
2026-05-12T09:22:12.427026Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=2 elapsed=1.759127041s
2026-05-12T09:22:12.427274Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 2 eligible frames
2026-05-12T09:22:12.869213Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 1 frames, 0.2MB → 0.3MB (0.9x), 1 JPEGs deleted
2026-05-12T09:22:13.304558Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 1 frames, 0.3MB → 0.4MB (0.9x), 1 JPEGs deleted
2026-05-12T09:22:39.009649Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-1944753676112650055, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T09:23:23.041658Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T09:25:08.112066Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-2757320308507279294, trigger=click)
2026-05-12T09:25:08.126094Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-2757320308507279294, trigger=click)
2026-05-12T09:25:08.743069Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-2757320308507279294, trigger=click)
2026-05-12T09:25:08.782136Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-2757320308507279294, trigger=click)
2026-05-12T09:25:18.022691Z WARN screenpipe_a11y::platform::macos: clipboard capture disabled — prior NSPasteboard crash detected. delete /Users/lukas/.screenpipe/clipboard-disabled-after-crash to re-enable
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buff...
|
iTerm2
|
screenpipe"
|
NULL
|
21820
|
|
26306
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:47:23.838686Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:49:10.556142Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=1 rows_returned=35 elapsed=1.320759208s
2026-05-12T14:49:10.556536Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 35 eligible frames
2026-05-12T14:49:12.093113Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 14 frames, 2.7MB → 0.3MB (8.9x), 14 JPEGs deleted
2026-05-12T14:49:13.889798Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 19 frames, 3.6MB → 0.7MB (4.9x), 19 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:49:26.762419Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:51:29.801432Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:51:55.611515Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 105.3ms elapsed (expected 5.3ms) → inserting 100.0ms silence (9598 samples)
2026-05-12T14:51:55.781428Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 169.9ms elapsed (expected 5.3ms) → inserting 164.6ms silence (15800 samples)
2026-05-12T14:51:56.081737Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 139.9ms elapsed (expected 5.3ms) → inserting 134.5ms silence (12914 samples)
2026-05-12T14:53:02.556928Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 85.7ms elapsed (expected 5.3ms) → inserting 80.4ms silence (7717 samples)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:53:33.473658Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:54:14.604527Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 57 eligible frames
2026-05-12T14:54:16.150850Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 23 frames, 4.4MB → 0.3MB (14.3x), 23 JPEGs deleted
2026-05-12T14:54:18.438626Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 32 frames, 5.7MB → 1.4MB (4.2x), 32 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:55:36.875217Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: install a starter bundle of pipes:
screenpipe install https://screenpi.pe/start.json
2026-05-12T14:56:43.513652Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6205158385764507775, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:57:43.527916Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:57:51.020481Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:57:54.005004Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:58:00.087355Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:58:03.103321Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:58:08.055814Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-9035457757750653601, trigger=click)
2026-05-12T14:58:08.062982Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=click)
2026-05-12T14:58:12.199518Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:59:20.391870Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=101 elapsed=1.967512791s
2026-05-12T14:59:20.392758Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 101 eligible frames
2026-05-12T14:59:22.488440Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 33 frames, 9.8MB → 1.0MB (9.7x), 33 JPEGs deleted
2026-05-12T14:59:29.272518Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 66 frames, 10.5MB → 4.5MB (2.3x), 66 JPEGs deleted
2026-05-12T14:59:34.683966Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9180842073176773313, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:59:47.398325Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:59:47.459122Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=3999125719128242167, trigger=click)
2026-05-12T14:59:50.807323Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 101.4ms elapsed (expected 5.3ms) → inserting 96.0ms silence (9219 samples)
2026-05-12T15:00:25.458921Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8147332135429607620, trigger=visual_change)
2026-05-12T15:00:28.452080Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8147332135429607620, trigger=visual_change)
2026-05-12T15:00:29.167946Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8147332135429607620, trigger=visual_change)
2026-05-12T15:00:38.277066Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8147332135429607620, trigger=click)
2026-05-12T15:00:39.475884Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8147332135429607620, trigger=click)
2026-05-12T15:00:58.089090Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7442982011400540096, trigger=click)
2026-05-12T15:00:58.095618Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7442982011400540096, trigger=click)
2026-05-12T15:01:02.550033Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-545273533072853505, trigger=visual_change)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:01:50.346393Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:03:52.628434Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T15:04:31.563819Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=140 elapsed=2.253134667s
2026-05-12T15:04:31.564540Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 140 eligible frames
2026-05-12T15:04:34.375276Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 47 frames, 15.0MB → 0.8MB (19.1x), 47 JPEGs deleted
2026-05-12T15:04:41.481988Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 91 frames, 13.6MB → 5.6MB (2.4x), 91 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:05:55.231679Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
2026-05-12T15:07:10.598829Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 82.8ms elapsed (expected 5.3ms) → inserting 77.5ms silence (7439 samples)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:07:57.738534Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T15:09:41.576620Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 110 eligible frames
2026-05-12T15:09:44.361015Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 46 frames, 13.4MB → 1.3MB (10.1x), 46 JPEGs deleted
2026-05-12T15:09:49.818095Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 62 frames, 10.4MB → 4.2MB (2.5x), 62 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:10:00.032837Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:12:02.830584Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:14:05.195695Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T15:14:53.091375Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=94 elapsed=3.184523292s
2026-05-12T15:14:53.091512Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 94 eligible frames
2026-05-12T15:14:55.411976Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 36 frames, 6.9MB → 1.0MB (6.6x), 36 JPEGs deleted
2026-05-12T15:15:00.362839Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 56 frames, 8.4MB → 3.7MB (2.3x), 56 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_i...
|
iTerm2
|
screenpipe"
|
NULL
|
26306
|
|
26307
|
ggml_metal_init: found device: Apple M1
ggml_metal ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:47:23.838686Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:49:10.556142Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=1 rows_returned=35 elapsed=1.320759208s
2026-05-12T14:49:10.556536Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 35 eligible frames
2026-05-12T14:49:12.093113Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 14 frames, 2.7MB → 0.3MB (8.9x), 14 JPEGs deleted
2026-05-12T14:49:13.889798Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 19 frames, 3.6MB → 0.7MB (4.9x), 19 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:49:26.762419Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:51:29.801432Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:51:55.611515Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 105.3ms elapsed (expected 5.3ms) → inserting 100.0ms silence (9598 samples)
2026-05-12T14:51:55.781428Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 169.9ms elapsed (expected 5.3ms) → inserting 164.6ms silence (15800 samples)
2026-05-12T14:51:56.081737Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 139.9ms elapsed (expected 5.3ms) → inserting 134.5ms silence (12914 samples)
2026-05-12T14:53:02.556928Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 85.7ms elapsed (expected 5.3ms) → inserting 80.4ms silence (7717 samples)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:53:33.473658Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:54:14.604527Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 57 eligible frames
2026-05-12T14:54:16.150850Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 23 frames, 4.4MB → 0.3MB (14.3x), 23 JPEGs deleted
2026-05-12T14:54:18.438626Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 32 frames, 5.7MB → 1.4MB (4.2x), 32 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:55:36.875217Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: install a starter bundle of pipes:
screenpipe install https://screenpi.pe/start.json
2026-05-12T14:56:43.513652Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=6205158385764507775, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:57:43.527916Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:57:51.020481Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:57:54.005004Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:58:00.087355Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:58:03.103321Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:58:08.055814Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-9035457757750653601, trigger=click)
2026-05-12T14:58:08.062982Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=click)
2026-05-12T14:58:12.199518Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9035457757750653601, trigger=visual_change)
2026-05-12T14:59:20.391870Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=101 elapsed=1.967512791s
2026-05-12T14:59:20.392758Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 101 eligible frames
2026-05-12T14:59:22.488440Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 33 frames, 9.8MB → 1.0MB (9.7x), 33 JPEGs deleted
2026-05-12T14:59:29.272518Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 66 frames, 10.5MB → 4.5MB (2.3x), 66 JPEGs deleted
2026-05-12T14:59:34.683966Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-9180842073176773313, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T14:59:47.398325Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T14:59:47.459122Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=3999125719128242167, trigger=click)
2026-05-12T14:59:50.807323Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 101.4ms elapsed (expected 5.3ms) → inserting 96.0ms silence (9219 samples)
2026-05-12T15:00:25.458921Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8147332135429607620, trigger=visual_change)
2026-05-12T15:00:28.452080Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8147332135429607620, trigger=visual_change)
2026-05-12T15:00:29.167946Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-8147332135429607620, trigger=visual_change)
2026-05-12T15:00:38.277066Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8147332135429607620, trigger=click)
2026-05-12T15:00:39.475884Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-8147332135429607620, trigger=click)
2026-05-12T15:00:58.089090Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7442982011400540096, trigger=click)
2026-05-12T15:00:58.095618Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7442982011400540096, trigger=click)
2026-05-12T15:01:02.550033Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-545273533072853505, trigger=visual_change)
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:01:50.346393Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:03:52.628434Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T15:04:31.563819Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=140 elapsed=2.253134667s
2026-05-12T15:04:31.564540Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 140 eligible frames
2026-05-12T15:04:34.375276Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 47 frames, 15.0MB → 0.8MB (19.1x), 47 JPEGs deleted
2026-05-12T15:04:41.481988Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 91 frames, 13.6MB → 5.6MB (2.4x), 91 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:05:55.231679Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
2026-05-12T15:07:10.598829Z WARN screenpipe_audio::core::source_buffer: [MacBook Pro Microphone (input)] large gap on wired device: 82.8ms elapsed (expected 5.3ms) → inserting 77.5ms silence (7439 samples)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:07:57.738534Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T15:09:41.576620Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 110 eligible frames
2026-05-12T15:09:44.361015Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 46 frames, 13.4MB → 1.3MB (10.1x), 46 JPEGs deleted
2026-05-12T15:09:49.818095Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 62 frames, 10.4MB → 4.2MB (2.5x), 62 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:10:00.032837Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:12:02.830584Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T15:14:05.195695Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T15:14:53.091375Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=94 elapsed=3.184523292s
2026-05-12T15:14:53.091512Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 94 eligible frames
2026-05-12T15:14:55.411976Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 36 frames, 6.9MB → 1.0MB (6.6x), 36 JPEGs deleted
2026-05-12T15:15:00.362839Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 56 frames, 8.4MB → 3.7MB (2.3x), 56 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_i...
|
iTerm2
|
screenpipe"
|
NULL
|
26307
|
|
27851
|
2026-05-12T17:17:42.677982Z INFO screenpipe_audio 2026-05-12T17:17:42.677982Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:18:14.517146Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:18:17.128270Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-685867194490231511, trigger=click)
2026-05-12T17:18:32.364497Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-105135387311717328, trigger=click)
2026-05-12T17:19:31.671240Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7531015335125464264, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:20:23.489792Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-12T17:22:33.570164Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=1 rows_returned=46 elapsed=3.214084166s
2026-05-12T17:22:33.571046Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 46 eligible frames
2026-05-12T17:22:36.792500Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 3.5MB → 0.6MB (6.1x), 24 JPEGs deleted
2026-05-12T17:22:40.775049Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=5883051214829112857, trigger=click)
2026-05-12T17:22:41.180662Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 19 frames, 3.3MB → 0.3MB (12.1x), 19 JPEGs deleted
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:22:47.773337Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:23:14.805309Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-3806421268519741354, trigger=click)
2026-05-12T17:23:52.318241Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7531015335125464264, trigger=click)
2026-05-12T17:23:53.971528Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7531015335125464264, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:24:53.043924Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
2026-05-12T17:26:18.879557Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-4754240751466450123, trigger=click)
2026-05-12T17:26:36.212023Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7531015335125464264, trigger=click)
2026-05-12T17:26:36.989863Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7531015335125464264, trigger=click)
2026-05-12T17:26:36.990537Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7531015335125464264, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:27:00.863405Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:27:41.320020Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 34 eligible frames
2026-05-12T17:27:42.818097Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 16 frames, 2.3MB → 0.2MB (13.2x), 16 JPEGs deleted
2026-05-12T17:27:44.477853Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 16 frames, 2.8MB → 0.3MB (10.2x), 16 JPEGs deleted
2026-05-12T17:28:37.970301Z INFO screenpipe_audio::audio_manager::manager: batch mode: deferral cap (600s) reached during active session, force-transcribing
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:28:46.101432Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 chunks
2026-05-12T17:28:59.838051Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=2491485282282992349, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:29:05.478909Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:29:31.491338Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=2491485282282992349, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:31:13.235812Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:32:20.048798Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-2261149417879810331, trigger=click)
2026-05-12T17:32:47.004117Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=103 elapsed=2.51008175s
2026-05-12T17:32:47.009643Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 103 eligible frames
2026-05-12T17:32:50.488130Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 51 frames, 7.3MB → 0.2MB (41.0x), 51 JPEGs deleted
2026-05-12T17:32:53.940730Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 50 frames, 8.8MB → 0.3MB (31.4x), 50 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:33:23.594769Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:34:28.508317Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=4204223135321042753, trigger=click)
2026-05-12T17:34:41.126226Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-685867194490231511, trigger=click)
2026-05-12T17:35:22.314262Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=4204223135321042753, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:35:31.665229Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=5883051214829112857, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:35:34.950341Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: install a starter bundle of pipes:
screenpipe install https://screenpi.pe/start.json
2026-05-12T17:36:23.344180Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-685867194490231511, trigger=click)
2026-05-12T17:36:45.994725Z INFO screenpipe_engine::meeting_detector: meeting v2: Active -> Ending (no controls, app=Firefox, id=7, grace=300s)
2026-05-12T17:37:05.984992Z INFO screenpipe_audio::audio_manager::manager: batch mode: audio session ended, transcribing accumulated audio
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:37:09.374972Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:37:38.487443Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:37:56.054143Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=148 elapsed=2.122874333s
2026-05-12T17:37:56.054671Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 148 eligible frames
2026-05-12T17:38:00.248393Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 73 frames, 10.5MB → 0.2MB (57.8x), 73 JPEGs deleted
2026-05-12T17:38:00.343831Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-936682655402305214, trigger=click)
2026-05-12T17:38:04.495544Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 73 frames, 12.8MB → 0.3MB (45.4x), 73 JPEGs deleted
2026-05-12T17:38:16.909419Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-936682655402305214, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_i...
|
iTerm2
|
screenpipe"
|
NULL
|
27851
|
|
27852
|
2026-05-12T17:17:42.677982Z INFO screenpipe_audio 2026-05-12T17:17:42.677982Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:18:14.517146Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:18:17.128270Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-685867194490231511, trigger=click)
2026-05-12T17:18:32.364497Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-105135387311717328, trigger=click)
2026-05-12T17:19:31.671240Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7531015335125464264, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:20:23.489792Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: sign in for higher AI quotas + cloud sync:
screenpipe login
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
2026-05-12T17:22:33.570164Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=1 rows_returned=46 elapsed=3.214084166s
2026-05-12T17:22:33.571046Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 46 eligible frames
2026-05-12T17:22:36.792500Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 24 frames, 3.5MB → 0.6MB (6.1x), 24 JPEGs deleted
2026-05-12T17:22:40.775049Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=5883051214829112857, trigger=click)
2026-05-12T17:22:41.180662Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 19 frames, 3.3MB → 0.3MB (12.1x), 19 JPEGs deleted
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:22:47.773337Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:23:14.805309Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-3806421268519741354, trigger=click)
2026-05-12T17:23:52.318241Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7531015335125464264, trigger=click)
2026-05-12T17:23:53.971528Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7531015335125464264, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:24:53.043924Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: get the screenpipe desktop app for the full experience
https://screenpi.pe
2026-05-12T17:26:18.879557Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-4754240751466450123, trigger=click)
2026-05-12T17:26:36.212023Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7531015335125464264, trigger=click)
2026-05-12T17:26:36.989863Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=7531015335125464264, trigger=click)
2026-05-12T17:26:36.990537Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=7531015335125464264, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:27:00.863405Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:27:41.320020Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 34 eligible frames
2026-05-12T17:27:42.818097Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 16 frames, 2.3MB → 0.2MB (13.2x), 16 JPEGs deleted
2026-05-12T17:27:44.477853Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 16 frames, 2.8MB → 0.3MB (10.2x), 16 JPEGs deleted
2026-05-12T17:28:37.970301Z INFO screenpipe_audio::audio_manager::manager: batch mode: deferral cap (600s) reached during active session, force-transcribing
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:28:46.101432Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 chunks
2026-05-12T17:28:59.838051Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=2491485282282992349, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:29:05.478909Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:29:31.491338Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=2491485282282992349, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
tip: wire screenpipe into claude with one command:
claude mcp add screenpipe -- npx -y screenpipe-mcp
then ask claude to build a pipe that tracks who you are, your todos, and how you spend your time from your screen activity
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:31:13.235812Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:32:20.048798Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-2261149417879810331, trigger=click)
2026-05-12T17:32:47.004117Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=103 elapsed=2.51008175s
2026-05-12T17:32:47.009643Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 103 eligible frames
2026-05-12T17:32:50.488130Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 51 frames, 7.3MB → 0.2MB (41.0x), 51 JPEGs deleted
2026-05-12T17:32:53.940730Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 50 frames, 8.8MB → 0.3MB (31.4x), 50 JPEGs deleted
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:33:23.594769Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:34:28.508317Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=4204223135321042753, trigger=click)
2026-05-12T17:34:41.126226Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-685867194490231511, trigger=click)
2026-05-12T17:35:22.314262Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=4204223135321042753, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:35:31.665229Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=5883051214829112857, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:35:34.950341Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
tip: install a starter bundle of pipes:
screenpipe install https://screenpi.pe/start.json
2026-05-12T17:36:23.344180Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-685867194490231511, trigger=click)
2026-05-12T17:36:45.994725Z INFO screenpipe_engine::meeting_detector: meeting v2: Active -> Ending (no controls, app=Firefox, id=7, grace=300s)
2026-05-12T17:37:05.984992Z INFO screenpipe_audio::audio_manager::manager: batch mode: audio session ended, transcribing accumulated audio
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:37:09.374972Z INFO screenpipe_audio::audio_manager::manager: batch mode: transcribed 50 chunks
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
2026-05-12T17:37:38.487443Z INFO screenpipe_audio::audio_manager::manager: reconciliation: transcribed 50 orphaned chunks
2026-05-12T17:37:56.054143Z WARN sqlx::query: summary="SELECT id, snapshot_path, device_name, …" db.statement="\n\nSELECT\n id,\n snapshot_path,\n device_name,\n timestamp\nFROM\n frames\nWHERE\n snapshot_path IS NOT NULL\n AND timestamp < ?1\nORDER BY\n device_name,\n timestamp ASC\nLIMIT\n 5000\n" rows_affected=0 rows_returned=148 elapsed=2.122874333s
2026-05-12T17:37:56.054671Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: found 148 eligible frames
2026-05-12T17:38:00.248393Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 73 frames, 10.5MB → 0.2MB (57.8x), 73 JPEGs deleted
2026-05-12T17:38:00.343831Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 2 (hash=-936682655402305214, trigger=click)
2026-05-12T17:38:04.495544Z INFO screenpipe_engine::snapshot_compaction: snapshot compaction: 73 frames, 12.8MB → 0.3MB (45.4x), 73 JPEGs deleted
2026-05-12T17:38:16.909419Z INFO screenpipe_engine::event_driven_capture: content dedup: skipping capture for monitor 1 (hash=-936682655402305214, trigger=click)
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_init: picking default device: Apple M1
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
whisper_backend_init: using BLAS backend
whisper_init_state: kv self size = 3.15 MB
whisper_init_state: kv cross size = 9.44 MB
whisper_init_state: kv pad size = 2.36 MB
whisper_init_state: compute buffer (conv) = 14.17 MB
whisper_init_state: compute buffer (encode) = 65.96 MB
whisper_init_state: compute buffer (cross) = 8.50 MB
whisper_init_state: compute buffer (decode) = 96.83 MB
ggml_metal_free: deallocating
whisper_backend_init_gpu: device 0: Metal (type: 1)
whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)
whisper_backend_init_gpu: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1
ggml_metal_i...
|
iTerm2
|
screenpipe"
|
NULL
|
27852
|
|
26238
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_f
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_f, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Plain Text
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 1, Col 1
Info: Downloading VS Code Server...
Implement and run pipe logic...
|
Code
|
screenpipe_f — screenpipe [SSH: nas]
|
NULL
|
26238
|
|
26239
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_f
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_f, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Plain Text
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 1, Col 1
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking...
|
Code
|
screenpipe_f — screenpipe [SSH: nas]
|
NULL
|
26239
|
|
26240
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_f
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_f, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Plain Text
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 1, Col 1
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking...
|
Code
|
screenpipe_f — screenpipe [SSH: nas]
|
NULL
|
26240
|
|
26241
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_f
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_f, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Plain Text
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 1, Col 1
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable....
|
Code
|
screenpipe_f — screenpipe [SSH: nas]
|
NULL
|
26241
|
|
26242
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_f
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_f, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Plain Text
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 1, Col 1
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in...
|
Code
|
screenpipe_f — screenpipe [SSH: nas]
|
NULL
|
26242
|
|
26243
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_f
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_f, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Plain Text
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 1, Col 1
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit...
|
Code
|
screenpipe_f — screenpipe [SSH: nas]
|
NULL
|
26243
|
|
26244
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_f
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_f, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Plain Text
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 1, Col 1
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN...
|
Code
|
screenpipe_f — screenpipe [SSH: nas]
|
NULL
|
26244
|
|
26245
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_f
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_f, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Plain Text
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 1, Col 1
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py...
|
Code
|
screenpipe_f — screenpipe [SSH: nas]
|
NULL
|
26245
|
|
26246
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26246
|
|
26247
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_fts_migrate.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26247
|
|
26248
|
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_fts_migrate.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 214, Col 74
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl http://localhost:8766/api/pipes
# Run a pipe
curl -X POST "http://localhost:8766/api/pipes/day-recap/run"
curl -X POST "http://localhost:8766/api/pipes/standup-update/run?d=2026-04-25"
Rebuild and restart
to pick up the changes:
Copy code to clipboard
cd /volume1/screenpipe/app
docker compose up --build -d
How it works:
Each
pipe.md
file is loaded dynamically — the frontmatter provides metadata and the body becomes the user prompt. Screenpipe data (app usage, browser URLs, OCR, audio) is injected as a Claude system message so the pipe prompt can reference it naturally. The "Read screenpipe skill first" line is stripped automatically.
The pipes directory inside Docker is
/data/pipes
(since
/volume1/screenpipe
→
/data
). You can override it with a
PIPES_DIR
env var if needed.
Message actions
pipe.md
pipe.md
where to place api key and can I use different keys
Thinking
Thinking
Bash
Read .env file
IN
cat /volume1/screenpipe/app/.env
Copy code to clipboard
OUT
[ENV_SECRET]
Where to place the key:
app/.env
app/.env
— replace
your_key_here
with your actual key:
Copy code to clipboard
[ENV_SECRET]
That file is loaded by
load_dotenv()
at startup and is excluded from git via
.gitignore
.
Can you use different keys per pipe?
Not currently — all pipes share the one key from
.env
. But you can add per-pipe key support by adding an
api_key
field to the pipe's frontmatter:
Copy code to clipboard
---
title: Meeting Summary
api_key_env: ANTHROPIC_KEY_MEETINGS
---
Then in
consumers/pipes.py
consumers/pipes.py
, read it in
_parse_frontmatter
and pass it through
run_pipe
. Want me to add that?
Message actions
pipe.md
pipe.md
can I use mistral or other llm? or is is build for antrophic only
Thinking
Thinking
Currently it's Anthropic-only — the code calls the
anthropic
SDK directly in both
consumers/pipes.py
consumers/pipes.py
and
consumers/summary.py
consumers/summary.py
.
Adding other providers is straightforward since Mistral, Ollama, OpenRouter, Groq, and most modern LLMs expose an OpenAI-compatible API. The cleanest approach: add the
openai
package and let you configure the provider via
.env
:
Copy code to clipboard
# Anthropic (default)
[ENV_SECRET]
# OR: any OpenAI-compatible provider
LLM_PROVIDER=openai-compatible
LLM_BASE_URL=https://api.mistral.ai/v1
[ENV_SECRET]
LLM_MODEL=mistral-small-latest
This would cover Mistral, Ollama (...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26248
|
|
26249
|
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_fts_migrate.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 200, Col 87
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26249
|
|
26250
|
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_fts_migrate.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 200, Col 87
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26250
|
|
26251
|
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_fts_migrate.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 25, Col 58
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26251
|
|
26252
|
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Explorer (⇧⌘E) - 2 unsaved files
2
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_fts_migrate.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 25, Col 58
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26252
|
|
26288
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26288
|
|
26289
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_fts_migrate.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 25, Col 58
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26289
|
|
26290
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_fts_migrate.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 32, Col 73
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26290
|
|
26291
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
11
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update, 1 requires restart
3
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_fts_migrate.sh
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
M
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_fts_migrate.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
#!/bin/bash
# screenpipe_fts_migrate.sh
# One-shot migration of the screenpipe NAS archive DB to the new schema:
# - adds install_id column to every synced base table
# - creates the _installs registry
# - rebuilds all four FTS tables as contentless with install_id + source_id
#
# This is OPTIONAL. screenpipe_sync.sh performs the same migration inline on
# its first run. The point of running this separately is SPEED: SQLite over
# SMB is slow due to fsync semantics, and the FTS rebuild reads every row
# of every base table. Running the rebuild locally on the NAS over SSH is
# typically 5-10x faster.
#
# Idempotent — safe to re-run. Detects the new schema and exits if already migrated.
#
# Usage
# -----
# On the NAS via SSH (recommended for archives > 1 GB):
# ssh Adm1n@[IP_ADDRESS]
# # copy this script over first, then:
# ./screenpipe_fts_migrate.sh /volume1/Test/screenpipe/archive.db
#
# On Mac (works but slower):
# ./screenpipe_fts_migrate.sh /Volumes/screenpipe/archive.db
# # or with no arg to use the default Mac mount path:
# ./screenpipe_fts_migrate.sh
set -euo pipefail
NAS_DB="${1:-/Volumes/screenpipe/archive.db}"
VISION_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
AUDIO_TABLES=(speakers speaker_embeddings audio_chunks audio_transcriptions audio_tags)
SHARED_TABLES=(tags vision_tags)
ALL_SYNC_TABLES=("${VISION_TABLES[@]}" "${AUDIO_TABLES[@]}" "${SHARED_TABLES[@]}")
FTS_TABLES=(frames_fts elements_fts ui_events_fts audio_transcriptions_fts)
# ─── HELPERS ──────────────────────────────────────────────────────────────────
table_exists() {
local count
count=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$1';")
[ "$count" -gt 0 ]
}
step() {
printf "\n▶ %s\n" "$*"
}
run_with_timer() {
local label="$1" sql="$2"
local start
start=$(date +%s)
printf " %-44s " "$label"
if sqlite3 "$NAS_DB" "$sql" > /dev/null 2>&1; then
local dur=$(( $(date +%s) - start ))
printf "✓ %dm%02ds\n" "$(( dur / 60 ))" "$(( dur % 60 ))"
else
printf "✗ FAILED\n"
sqlite3 "$NAS_DB" "$sql" # re-run to surface the error
exit 1
fi
}
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
[ -f "$NAS_DB" ] || { echo "ERROR: $NAS_DB not found"; exit 1; }
echo "================================================"
echo "Screenpipe FTS migration"
echo "DB: $NAS_DB"
echo "Size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
# ─── STEP 1: install registry ─────────────────────────────────────────────────
step "Creating install registry"
run_with_timer "_installs table" "
CREATE TABLE IF NOT EXISTS _installs (
install_id TEXT PRIMARY KEY,
install_seq INTEGER NOT NULL UNIQUE,
first_seen TEXT NOT NULL DEFAULT (datetime('now')),
last_seen TEXT NOT NULL DEFAULT (datetime('now'))
);
"
# ─── STEP 2: install_id on base tables ────────────────────────────────────────
step "Adding install_id to base tables"
LEGACY_TAG="legacy-$(date +%Y%m%d)"
LEGACY_USED=false
for tbl in "${ALL_SYNC_TABLES[@]}"; do
if ! table_exists "$tbl"; then
printf " %-44s (table not present, skipping)\n" "$tbl"
continue
fi
HAS_COL=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM pragma_table_info('$tbl') WHERE name='install_id';")
if [ "$HAS_COL" = "0" ]; then
ROW_COUNT=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM $tbl;")
printf " %-44s adding (backfill %s rows)\n" "$tbl" "$ROW_COUNT"
sqlite3 "$NAS_DB" "ALTER TABLE $tbl ADD COLUMN install_id TEXT;"
sqlite3 "$NAS_DB" "UPDATE $tbl SET install_id = '$LEGACY_TAG' WHERE install_id IS NULL;"
[ "$ROW_COUNT" -gt "0" ] && LEGACY_USED=true
else
printf " %-44s already present\n" "$tbl"
fi
if [ "$tbl" = "vision_tags" ]; then
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_vision_tags_install_pk ON vision_tags(install_id, vision_id, tag_id);"
else
sqlite3 "$NAS_DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx_${tbl}_install_pk ON ${tbl}(install_id, id);"
fi
done
if [ "$LEGACY_USED" = true ]; then
sqlite3 "$NAS_DB" "
INSERT OR IGNORE INTO _installs(install_id, install_seq, first_seen, last_seen)
VALUES ('$LEGACY_TAG', (SELECT COALESCE(MAX(install_seq),0)+1 FROM _installs), 'pre-migration', 'pre-migration');
"
fi
# ─── STEP 3: detect old FTS ───────────────────────────────────────────────────
OLD_FTS_DETECTED=false
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
SCHEMA_SQL=$(sqlite3 "$NAS_DB" "SELECT sql FROM sqlite_master WHERE name='$fts';")
if echo "$SCHEMA_SQL" | grep -q "content=" || ! echo "$SCHEMA_SQL" | grep -q "install_id"; then
OLD_FTS_DETECTED=true
break
fi
fi
done
if [ "$OLD_FTS_DETECTED" = false ]; then
echo ""
echo "FTS tables already on the new schema — nothing to rebuild."
echo "Migration complete."
exit 0
fi
# ─── STEP 4: rebuild FTS tables ───────────────────────────────────────────────
step "Rebuilding FTS tables (this is the slow part)"
for fts in "${FTS_TABLES[@]}"; do
if table_exists "$fts"; then
run_with_timer "drop old $fts" "DROP TABLE $fts;"
fi
done
run_with_timer "create frames_fts" "
CREATE VIRTUAL TABLE frames_fts USING fts5(
full_text, app_name, window_name, browser_url,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create elements_fts" "
CREATE VIRTUAL TABLE elements_fts USING fts5(
text, role,
install_id UNINDEXED, source_id UNINDEXED, frame_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create ui_events_fts" "
CREATE VIRTUAL TABLE ui_events_fts USING fts5(
text_content, app_name, window_title, element_name,
install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
run_with_timer "create audio_transcriptions_fts" "
CREATE VIRTUAL TABLE audio_transcriptions_fts USING fts5(
transcription, device,
speaker_id UNINDEXED, install_id UNINDEXED, source_id UNINDEXED,
tokenize='unicode61'
);
"
# Populate from base tables. The slow operations live here.
if table_exists "frames"; then
run_with_timer "populate frames_fts" "
INSERT INTO frames_fts(full_text, app_name, window_name, browser_url, install_id, source_id)
SELECT full_text, app_name, window_name, browser_url, install_id, id
FROM frames WHERE full_text IS NOT NULL AND full_text != '';
"
fi
if table_exists "elements"; then
run_with_timer "populate elements_fts" "
INSERT INTO elements_fts(text, role, install_id, source_id, frame_id)
SELECT text, role, install_id, id, frame_id
FROM elements WHERE text IS NOT NULL;
"
fi
if table_exists "ui_events"; then
run_with_timer "populate ui_events_fts" "
INSERT INTO ui_events_fts(text_content, app_name, window_title, element_name, install_id, source_id)
SELECT text_content, app_name, window_title, element_name, install_id, id
FROM ui_events WHERE text_content IS NOT NULL;
"
fi
if table_exists "audio_transcriptions"; then
run_with_timer "populate audio_transcriptions_fts" "
INSERT INTO audio_transcriptions_fts(transcription, device, speaker_id, install_id, source_id)
SELECT transcription, COALESCE(device,''), speaker_id, install_id, id
FROM audio_transcriptions WHERE transcription IS NOT NULL AND transcription != '';
"
fi
echo ""
echo "================================================"
echo "Migration complete."
echo "Final DB size: $(du -sh "$NAS_DB" | cut -f1)"
echo "================================================"
echo ""
echo "Sanity-check queries you can run:"
echo " sqlite3 $NAS_DB 'SELECT * FROM _installs;'"
echo " sqlite3 $NAS_DB \"SELECT sql FROM sqlite_master WHERE name='frames_fts';\""
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM frames_fts;'"
echo " sqlite3 $NAS_DB 'SELECT COUNT(*) FROM audio_transcriptions_fts;'"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
Remote - SSH - Output
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 4
Ln 26, Col 34
Info: Downloading VS Code Server...
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl http://localhost:8766/api/pipes
# Run a pipe
curl -X POST "http://localhost:8766/api/pipes/day-recap/run"
curl -X POST "http://localhost:8766/api/pipes/standup-update/run?d=2026-04-25"
Rebuild and restart
to pick up the changes:
Copy code to clipboard
cd /volume1/screenpipe/app
docker compose up --build -d
How it works:
Each...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26291
|
|
26297
|
Explorer (⇧⌘E) - 1 unsaved file
iTerm2ShellEditV Explorer (⇧⌘E) - 1 unsaved file
iTerm2ShellEditViewSessionScriptsProfilesWindowHelpRetro - Platform - in 1h 41 m100% <78• Tue 12 May 15:19:08DOCKERDOCKER (-zsh)STAGE (ssh)₴81DEV (-zsh)O $2APP (-zsh)883ec2-user@ip-10-30-129-.84T2PROD (-zsh)181screenpipe*kibanaasticsearch"{"type" : "log""@timestamp": "2026-05-11T19:54:53Z","tags" : ["warning","el,"data"], "pid" :7,'"message": "Unabletorevive connection: [URL_WITH_CREDENTIALS] : "2026-05-11T19:54:53Z",asticsearch", "data"],"pid":7,"message": "No livingconnections"}["warning".,"elkibanaI {"type" : "log", "@timestamp" : "2026-05-11T19:54:53Z"ugins""licensing"], "pid" :7,"message" : "License informationasticsearch due to Error: No Livingconnectionskibana1 {"type" : "log","@timestamp": "2026-05-11T19:54:54Z","tags" : ["error"ticsearch", "data"], "pid":7, "message" : "[ConnectionError]: getaddrinfo ENOTFOUND elasticsearch elasticsearch: 9200"}kibana1 {"type" : "log","@timestamp": "2026-05-11T19:54:54Z", "tags" : ["warning", "elasticsearch", "data"], "pid" :7,"message":"Unable to reviveconnection: [URL_WITH_CREDENTIALS] "2026-05-11T19:54:54Z","tags" : ["warning", "elasticsearch", "data"],"pid":7,"message"• "No livingconnections"}kibana1 {"type": "log","@timestamp": "2026-05-11T19:54:54Z""tags" : ["error", "plugins", "taskManager""taskManager"], "pid":7, "message": "Failed to poll for work: Error: NoLiving connections"}kibana1 {"type": "log", "@timestamp": "2026-05-11T19:54:572", "tags" : ["error", "elasticsearch".,"data"], "pid" :7, "message" :"[ConnectionError]: getaddrinfo ENOTFOUND elasticsearch elasticsearch:9200*}kibana1 {"type" : "Log","@timestamp" : "2026-05-11T19:54:57Z","tags" : ["warning","elasticsearch", "data"], "pid" :7, "message": "Unable to revive connection: [URL_WITH_CREDENTIALS] : "2026-05-11T19:54:57Z", "tags" : ["warning", "elasticsearch", "data"], "pid" :7, "message": "No living connections"}kibanaI {"type" : "log", "@timestamp" : "2026-05-11T19:54:57Z", "tags" : ["error","plugins", "taskManager", "taskManager"], "pid" :7, "message" : "Failed to pollfor work: Error: NoLiving connections"}kibanaI {"type" : "log", "@timestamp" : "2026-05-11T19:54:59Z","tags" : ["error", "elasticsearch", "data"], "pid" :7, "message" : "[ConnectionError]: getaddrinfo ENOTFOUND elasticsearch elasticsearch:9200"}1 {"type" : "log","@timestamp": "2026-05-11T19:55: 00Z""tags": ["warning"asticsearch", "data"], "pid" :7, "message": "Unable to revive connection: [URL_WITH_CREDENTIALS] : "2026-05-11T19:55 :00Z", "tags" : ["warning", "elasticsearch", "data"], "pid" :7, "message": "No living connections"}1 {"type": "log", "@timestamp" : "2026-05-11T19:55:00Z","tags" : ["error", "plug, "taskManager",, "taskManager"], "pid" :7, "message": "Failed to poll for work: Error: NoLiving connections"}unexpected EOFkas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~/jiminny/infrastructure/dev/docker (develop) $-zshX5O 886-zsh*** System restart required ***Last login: Thu May7 08:01:13 2026 from 212.5.153.87lukas@jiminny-prod-bastion:~$lukas@jiminny-prod-bastion:~$ client_loop: send disconnect: Broken pipeukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ ||XIT3 EU (ssh)New release '24.04.4 LTS' available.Run'do-release-upgrade' to upgrade to it.*** System restart required ***Last login: Wed Apr 22 08:09:46 2026 from 212.5.153.87lukas@jiminny-eu-bastion:~$ 0T4STAGE (ssh)Run 'do-release-upgrade' to upgrade to it.System restart required ***Last login: Thu May7 11:01:47 2026 from 212.5.153.87bastion:-$QA (-zsh)Poetry could not find a pyproject.toml file in /Users/lukas or its parentsPoetry could not find a pyproject.toml file in /Users/lukas or its parentsT6FE (-zsh)Poetry could not find a pyproject.toml file in /Users/lukas or its parentsPRODSTAGEFRONTENDPoetry could not find a pyproject.toml file in /Users/lukas or its parentsLukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ |17 EXT (-zsh)Poetry could not find a pyproject.toml file in /Users/lukas or its parentsPoetry could not find a pyproject.toml file in /Users/lukas or its parentsukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ lEXTENSION...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26297
|
|
26298
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 11 pending changes
VIeWWindowmeltEXPLORERV SCREENPIPE [SSH: NAS]• #recycle› app› logs• gitignore() app_settings.jsonE archive.dlE archive.db-bak= db.saliteE db.salite-shm= db.salite-wal$ screenpipe_fts_migrate.shS screenoioe sunc uodated.sh$ screenpine svnc.sh= screennine.dbOUTIINE> TIMELINEes apo_settinas.ison*SSH: nas i&master ( @0A0 (g)1screenpipe sync.shMs screenpipe tts migrate.sh Xscreenpipe sunc updated.shupipe.md$ screenpipe_fts_migrate.shfor tbl in105EEEEБEВ123125"STALL SYNC TABLES a": doelsesqlite3 "SNAS DB" "CREATE UNIQUE INDEX IF NOT EXISTS idx ${tbl} install pk ON S{tbl}(install id, id):"I "SLEGACY USED" = true : thensOUite? "SNAS DR""INSERT OR IGNORE INTO installs(install id, install_ seq, first seen, last_ seen)VALUES ('$LEGACY_ TAG', (SELECT COALESCE(MAX(install_ seq),0)+1 FROM installs), 'pre-migration', 'pre-migration');STEP 3: detect old FTStor FTSLES(@J}"; docdole exists oris, chetSCHEMA SQL=$(sqlite3 "$NAS DB" "SELECT sql FROM sqlite master WHERE name='$fts';")iT echo "SSChcMAsUL" orep -o "contene" echo"SSCHEMA SUL"-q "install id"; thenOLD FTs DETECTED=truebreakif [ "SOLD_FTS_DETECTED" = false ]; thenecho "g rabtes olreat, n the ner schens - nothing to rebuftl,.STEP 4:rebuild FTS tablesstep "Rebuilding FTS tables (this is the slow part)'for fts in "S{FTS TABLES[@]}": ddit table exists "Stts" therun with timer "droo old Sfts" "DROP TABLE SttS:"run with timer #create frames f+cl "GRFATE VTPTLIAL TARIE framec f+c IISTNG f+c5/window_name, browser_url,OUTPUTDEBUG CONSOLEPORTS (1.[15:12:54) Getting Manifest…ing extensiepinned: talse,productVersion: { version: '1.119.0', date: '2026-05-05T11:23:50-07:00' }.115:12:54.845operation: 3,isAppLicationScoped: false."/home/Admin/.vscode-server/extensions/extensions.ison'115.12-591 Extension simnature verification result for anthronic claude-code. Success Internal Code. 0. Execntede tme Duratione 12[15:13:00] Extracted extension to [URL_WITH_CREDENTIALS] /volume1/Test/screenpipe/archive.db /volume1/Test/screeIfanvthing goes sidewavs vou restore from this and re-run the oldscript.2. Pause the cron iob to avoid a race with the migration:crontab -e# comment out the screenpipe sync.sh line3. Pick a migration path.Path A - tast recommended itarchive is more than ~1 GB. runithe migration on the NAS over SSHYou're out of extra usage • Your limit resets at 7:20 PMBuy moreWrite a message…Opus 47 AdaptivevClaudo ic Aland can make mictakec Plosce double-chockr•ketro - Platomm • In 1h 41m100% 2• Tue 12 May 15:19:08screenplpe res migrate ohcopyspeaker 1d UNINDEXED, 1nstall 1d UNINDEXED, SOUrce 10 UNINDEXED175176if table exists "frames": thenrun_with_timer "populate frames_fts""INSERT INTO frames ftsful text, app name, window name. browser urinstalb id. source id)SELECT fub text. app name. window name, browser uni, instab id. idFROM frames WHERE full text IS NOT NULL AND fuil text 1e 11.if table exists "elements". thenrun with timer "populate elements fts"INSERT INTO elements fts(text, role, install id, source id, frame idSELECT text, role, install id, id, frame idGROM elomonte WHERE tovt TC NOT NulI•iT caole exists "ul events, chenrun with timer "populate vi events fts" "INSERT INTO U1 events Ttstext content, app name, window title, element name, instal 1d, source 1d)SELECT text content, app name, window title, element name, install id,FROM u1 events WHERE text content is Not NULL,if table exists "audio transcriptions": then"populate audio transcriptions fts""INSERT INTO audio transcriptions fts(transcription. device, speaker id install id source 1d)SELECT transcription, COALESCE(device,''), speaker_id, install_id, idFROM audio transcrintions WHERE transcrintion IS NOT NULL AND transcriotion le 11.207echo "Migration complete.""Final DB size: $(du -sh "$NAS_DB" | cut -f1)"echo "Sanity-check queries you can run:"echo "sqlite3 $NAS DB 'SELECT * FROM installs:'"echo"sglite3 $NAS DB \"SELECT sql FROM sglite master WHERE name='frameochn nsalite3 $NAS DB 'SELECT COUNT(*) FROM frames fts:'*echo"salite3 $NAS DB 'SELECT COUNT(*) FROM audio transcriptions fts:'...
|
Code
|
screenpipe_fts_migrate.sh — screenpipe [SSH: nas]
|
NULL
|
26298
|
|
21081
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
screenpipe_sync.sh, Editor Group 1
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 30, Col 2
git-commit Lukas Kovalik (2 weeks ago)
Lukas Kovalik (2 weeks ago)
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line
Now add the pipe endpoints at the end of main.py, before the closing summary section:
Edit
main.py
main.py
Added 14 lines
Now add the CLI command to
cli.py
cli.py
:
Edit
cli.py
cli.py
Added 40 lines
Done. Here's how to run pipes:
How to run pipes
How to run pipes
Via Docker (inside the running container):
Copy code to clipboard
docker exec -it screenpipe-app python cli.py pipe --list
docker exec -it screenpipe-app python cli.py pipe day-recap
docker exec -it screenpipe-app python cli.py pipe standup-update --date yesterday
Via the API
(once the container is running on port 8766):
Copy code to clipboard
# List pipes
curl http://localhost:8766/api/pipes
# Run a pipe
curl -X POST "http://localhost:8766/api/pipes/day-recap/run"
curl -X POST "http://localhost:8766/api/pipes/standup-update/run?d=2026-04-25"
Rebuild and restart
to pick up the changes:
Copy code to clipboard
cd /volume1/screenpipe/app
docker compose up --build -d
How it works:
Each
pipe.md
file is loaded dynamically — the frontmatter provides metadata and the body becomes the user prompt. Screenpipe data (app usage, browser URLs, OCR, audio) is injected as a Claude system message so the pipe prompt can reference it naturally. The "Read screenpipe skill first" line is stripped automatically.
The pipes directory inside Docker is
/data/pipes
(since
/volume1/screenpipe
→
/data
). You can override it with a
PIPES_DIR
env var if needed.
Message actions
pipe.md
pipe.md
where to place api key and can I use different keys
Thinking
Thinking
Bash
Read .env file
IN
cat /volume1/screenpipe/app/.env
Copy code to clipboard
OUT
[ENV_SECRET]...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21081
|
|
21082
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21082
|
|
21083
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21083
|
|
21094
|
iTerm2ShellEditViewSessionScriptsProfilesWindowHel iTerm2ShellEditViewSessionScriptsProfilesWindowHelp-zshDOCKER* *81DEV (docker)Last login: Sun May 10 21:10:26 on ttys013₴2APP (-zsh)883-zshPoetry could not find a pyproject.toml file in /Users/lukas or its parentsPoetry could not find a pyproject.toml file in /Users/lukas or its parentslukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~ $ cat ~/.screenpipe/screenpipe_sync.sh | pbcopylukas@Lukas-Kovaliks-MacBook-Pro-Jiminny ~$-zsh*5screenpipe"100% <47*8•Mon 11 May 20:12:01T81• ÷6-zshX7...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21094
|
|
21095
|
screenpipe sync.sh — screenpipe SSH: nas100% 12P• screenpipe sync.sh — screenpipe SSH: nas100% 12P• мon 11 May 20.12-0108000SioV SCREENPIPE ISSH: NASI> #recycleconsumers> static• .env& cli.py# db.pv•docker-compose.vmli# Dockertilemain.py=requirements.txt→data>logs→oinec• aitianore* aoo settinas.ison=archive.db=archive.db-bal= db salite= dh calite.chmE dh calite-wall$ screennine svnc undated shi$ screenpipe sync.snE screennine dhs apo settinas.isonNUANANN47$ screenpipe sync.sh X•pipe.md• .env* Syncs yesterday (derault)sh 2026-04-15screenpipe sync.sh today# syncs today so farat 3am0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh > /Users/lukas/.screenpipe/sync.log 2>&1-euo pipefailCONFIGDB SRC="S(SCREENPIPE DB:-SHOME/.screenpipe/db.salite}"NAS MOUNIE"SINAS MOUNT:- Volumes Test//screendioe?"NAS DB="<NAS MOUNT/archiive.db"NAS DATA-"CNAS MOUNT /data"LOG FILE="$HOME/.screenpipe/sync.log'SCRIPT_START=$(date +%)local msg="[$(date '+%Y-%m-%d %H:%M:&S')] $**ecno suse" ceend SLus relestep)local now=S(date +%s)]loca elaosedes now - SCRIPT START))Ilocal min=s( elansed ( 60)local sec=s( elansed % 60))printf "\n[+%02dm%02ds] • %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"run salite heredoc() {local startes date +%slprintf"9-26c " "clahel"sqLites"SDB SRC" <<< "$sql" &[PASSWORD_DOTS]g.•g.р*)PROBLEMSOUTPUTAdm1nanypAg00pi lIC_R55g: /volume1/ccreenninee* MI23 Implement and run pipe l..Implement and run oipe logleAamin@DXP4800PLUS-B5F8:/volumel//screenpipe/apps sudo docker exec -it screenpipe-app python cli.py pipe day-recap -=date 2026-04-20Running pipe 'day-recap' for 2026-04-20...• Thinking >• The container started before you updated the .env, so it's using the old placeholder key. Restart it to pick up the new one:ca /vo lumel/screenpipe/appsudo docker compose restart screenoine-aooThen try adain:sudo docker exec -it screenpipe-app python cli.py pipe day-recap --date 2026-04-20Adm1n@DXP4800PLUS-B5F8:/volume1/screenpipe/app$ sudo docker exec -it screenpipe-app python cli.py pipe day-recap --date 2026-04-20Runnina nine 'dav-recan' for 2026-04.20..key is there now but Admin@DXP4800PLUS-B5F8:/volume1/screenpipe/app$ sudo docker exec -it screenpipe-app python cli.py pipe day-recap --date 2026-04-20Runnina oioe 'dav-recao' for 2026-04-20.1• The kev works — it authenticated successfullv. The error is iust that vour Anthropic account has no credits. Go to console.anthropic.com → Plans & Billina and add some credits (a few dollars is enouah fotesting)Once topped up, rerun the same command and it should work.* Esc to focus or unfocus ClaudeM screenpipe_sync.sh€Ask before edit.bash +vO@•|sxOUTIING> TIMELINE*SSH: nas 8 master* ©@0A0 @10 Lukas Kovalik (2 weeks ago) Ln 26, Col 1 Spaces: 2 UTF-8 LF () Shell Script 8 Sign In...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21095
|
|
21096
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 40, Col 23
git-commit Lukas Kovalik (2 weeks ago)
Lukas Kovalik (2 weeks ago)
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.parti...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21096
|
|
21097
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 39, Col 1
git-commit Lukas Kovalik (2 weeks ago)
Lukas Kovalik (2 weeks ago)
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partit...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21097
|
|
21098
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 39, Col 1
git-commit Lukas Kovalik (2 weeks ago)
Lukas Kovalik (2 weeks ago)
Info: Setting up SSH Host nas: Setting up SSH tunnel
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range....
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21098
|
|
21099
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 352, Col 47 (13096 selected)
git-commit Lukas Kovalik (2 weeks ago)
Lukas Kovalik (2 weeks ago)
Info: Setting up SSH Host nas: Setting up SSH tunnel...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21099
|
|
21100
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 29, Col 35
git-commit Lukas Kovalik (2 weeks ago)
Lukas Kovalik (2 weeks ago)
No results found
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21100
|
|
21101
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21101
|
|
21102
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 29, Col 35
git-commit Lukas Kovalik (2 weeks ago)
Lukas Kovalik (2 weeks ago)
No results found
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21102
|
|
21103
|
Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧ Explorer (⇧⌘E)
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/Test/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables, indexes, FTS"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks
SELECT * FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames
SELECT * FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text
SELECT o.* FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events
SELECT * FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements
SELECT e.* FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings
SELECT * FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 352, Col 47 (13096 selected)
git-commit Lukas Kovalik (2 weeks ago)
Lukas Kovalik (2 weeks ago)
No results found
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = li...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21103
|
|
21104
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Schema-drift tolerant: if Screenpipe migrations add new columns to the source DB,
# the NAS archive gets ALTER TABLE'd to match. Inserts use explicit column lists,
# so positional mismatches can't occur.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# Tables that get schema drift handling. Order matters for FK-ish references
# (parents before children: video_chunks → frames → elements/ocr_text/ui_events).
SYNC_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ─── SCHEMA HELPERS ───────────────────────────────────────────────────────────
# Echoes "name|type" lines for a table from a given DB.
table_columns_with_types() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2 "|" $3}'
}
# Echoes just column names, one per line.
table_columns() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2}'
}
# Returns true (0) if a table exists in the given DB.
table_exists() {
local db="$1" table="$2"
local count
count=$(sqlite3 "$db" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$table';")
[ "$count" -gt 0 ]
}
# Adds any columns present in source but missing in NAS for the given table.
# Uses ALTER TABLE ADD COLUMN, which is a fast metadata-only operation in SQLite.
ensure_columns() {
local table="$1"
local label="schema: $table"
printf " %-36s " "$label"
if ! table_exists "$DB_SRC" "$table"; then
printf "✗ source missing — skipping\n"
return 0
fi
if ! table_exists "$NAS_DB" "$table"; then
printf "✓ fresh (created above)\n"
return 0
fi
local src_cols
src_cols=$(table_columns_with_types "$DB_SRC" "$table")
local nas_cols
nas_cols=$(table_columns "$NAS_DB" "$table")
local added=0
local added_names=""
while IFS='|' read -r name type; do
[ -z "$name" ] && continue
# Use grep -F -x for fixed-string exact match (safe against regex chars).
if ! echo "$nas_cols" | grep -Fxq "$name"; then
# SQLite ALTER TABLE ADD COLUMN: type is optional, no NOT NULL allowed
# without a constant default. Default-NULL is exactly what we want for archive.
sqlite3 "$NAS_DB" "ALTER TABLE $table ADD COLUMN \"$name\" $type;"
added=$((added + 1))
added_names="$added_names $name"
fi
done <<< "$src_cols"
if [ "$added" -gt 0 ]; then
printf "✓ added %d:%s\n" "$added" "$added_names"
else
printf "✓ in sync\n"
fi
}
# Echoes a comma-separated list of source columns for a table, double-quoted
# so reserved words and hyphens are safe. If an alias is provided, columns are
# prefixed (e.g. `o."col"`). Used for both INSERT and SELECT sides; aliased
# form is required when SELECTing from a JOIN where column names collide
# (e.g. ocr_text and frames both have app_name, window_name).
build_col_list() {
local table="$1"
local alias="${2:-}"
local prefix=""
[ -n "$alias" ] && prefix="${alias}."
table_columns "$DB_SRC" "$table" | awk 'NF' | awk -v p="$prefix" '{print p "\"" $0 "\""}' | paste -sd, -
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
if table_exists "$NAS_DB" "frames"; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "exists, no frames table yet"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables (CREATE IF NOT EXISTS)"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
# ─── SCHEMA DRIFT FIX ─────────────────────────────────────────────────────
# Runs AFTER CREATE IF NOT EXISTS so newly-created tables are no-ops here,
# and pre-existing tables get any missing columns added.
step "Reconciling NAS schema with source"
for tbl in "${SYNC_TABLES[@]}"; do
ensure_columns "$tbl"
done
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_frames_document_path ON frames(document_path) WHERE document_path IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_onscreen_frame ON elements(frame_id) WHERE on_screen = 1 AND text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── BUILD EXPLICIT COLUMN LISTS ──────────────────────────────────────────
# After ensure_columns, source ⊆ NAS for every synced table, so source's
# column list is a safe subset to use on both sides of the INSERT.
# For tables that JOIN frames (ocr_text, elements), the SELECT side needs
# alias-qualified columns because both tables share names (app_name, etc).
FRAMES_COLS=$(build_col_list frames)
ELEMENTS_COLS=$(build_col_list elements)
ELEMENTS_COLS_E=$(build_col_list elements e)
UI_EVENTS_COLS=$(build_col_list ui_events)
OCR_TEXT_COLS=$(build_col_list ocr_text)
OCR_TEXT_COLS_O=$(build_col_list ocr_text o)
VIDEO_CHUNKS_COLS=$(build_col_list video_chunks)
MEETINGS_COLS=$(build_col_list meetings)
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks ($VIDEO_CHUNKS_COLS)
SELECT $VIDEO_CHUNKS_COLS FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames ($FRAMES_COLS)
SELECT $FRAMES_COLS FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text ($OCR_TEXT_COLS)
SELECT $OCR_TEXT_COLS_O FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events ($UI_EVENTS_COLS)
SELECT $UI_EVENTS_COLS FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements ($ELEMENTS_COLS)
SELECT $ELEMENTS_COLS_E FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings ($MEETINGS_COLS)
SELECT $MEETINGS_COLS FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
# Screenpipe writes daily logs to ~/.screenpipe/screenpipe.YYYY-MM-DD.N.log
# (N is a rotation counter, almost always 0). Mirror them to NAS so log
# analysis can happen on the consumer side without SSH'ing back to the Mac.
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
# Use a glob with nullglob so an empty match doesn't expand to a literal pattern.
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
# No --ignore-existing here: logs grow during the day, so we want rsync's
# default size+mtime check to refresh files that have changed.
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
COPIED=${#LOG_FILES[@]}
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "$COPIED" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
# Mirror this script's own logbook to NAS so sync health can be monitored
# from the consumer side. Done last so the summary lines above are included.
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Schema-drift tolerant: if Screenpipe migrations add new columns to the source DB,
# the NAS archive gets ALTER TABLE'd to match. Inserts use explicit column lists,
# so positional mismatches can't occur.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# Tables that get schema drift handling. Order matters for FK-ish references
# (parents before children: video_chunks → frames → elements/ocr_text/ui_events).
SYNC_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ─── SCHEMA HELPERS ───────────────────────────────────────────────────────────
# Echoes "name|type" lines for a table from a given DB.
table_columns_with_types() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2 "|" $3}'
}
# Echoes just column names, one per line.
table_columns() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2}'
}
# Returns true (0) if a table exists in the given DB.
table_exists() {
local db="$1" table="$2"
local count
count=$(sqlite3 "$db" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$table';")
[ "$count" -gt 0 ]
}
# Adds any columns present in source but missing in NAS for the given table.
# Uses ALTER TABLE ADD COLUMN, which is a fast metadata-only operation in SQLite.
ensure_columns() {
local table="$1"
local label="schema: $table"
printf " %-36s " "$label"
if ! table_exists "$DB_SRC" "$table"; then
printf "✗ source missing — skipping\n"
return 0
fi
if ! table_exists "$NAS_DB" "$table"; then
printf "✓ fresh (created above)\n"
return 0
fi
local src_cols
src_cols=$(table_columns_with_types "$DB_SRC" "$table")
local nas_cols
nas_cols=$(table_columns "$NAS_DB" "$table")
local added=0
local added_names=""
while IFS='|' read -r name type; do
[ -z "$name" ] && continue
# Use grep -F -x for fixed-string exact match (safe against regex chars).
if ! echo "$nas_cols" | grep -Fxq "$name"; then
# SQLite ALTER TABLE ADD COLUMN: type is optional, no NOT NULL allowed
# without a constant default. Default-NULL is exactly what we want for archive.
sqlite3 "$NAS_DB" "ALTER TABLE $table ADD COLUMN \"$name\" $type;"
added=$((added + 1))
added_names="$added_names $name"
fi
done <<< "$src_cols"
if [ "$added" -gt 0 ]; then
printf "✓ added %d:%s\n" "$added" "$added_names"
else
printf "✓ in sync\n"
fi
}
# Echoes a comma-separated list of source columns for a table, double-quoted
# so reserved words and hyphens are safe. If an alias is provided, columns are
# prefixed (e.g. `o."col"`). Used for both INSERT and SELECT sides; aliased
# form is required when SELECTing from a JOIN where column names collide
# (e.g. ocr_text and frames both have app_name, window_name).
build_col_list() {
local table="$1"
local alias="${2:-}"
local prefix=""
[ -n "$alias" ] && prefix="${alias}."
table_columns "$DB_SRC" "$table" | awk 'NF' | awk -v p="$prefix" '{print p "\"" $0 "\""}' | paste -sd, -
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
if table_exists "$NAS_DB" "frames"; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "exists, no frames table yet"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables (CREATE IF NOT EXISTS)"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
# ─── SCHEMA DRIFT FIX ─────────────────────────────────────────────────────
# Runs AFTER CREATE IF NOT EXISTS so newly-created tables are no-ops here,
# and pre-existing tables get any missing columns added.
step "Reconciling NAS schema with source"
for tbl in "${SYNC_TABLES[@]}"; do
ensure_columns "$tbl"
done
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_frames_document_path ON frames(document_path) WHERE document_path IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_onscreen_frame ON elements(frame_id) WHERE on_screen = 1 AND text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── BUILD EXPLICIT COLUMN LISTS ──────────────────────────────────────────
# After ensure_columns, source ⊆ NAS for every synced table, so source's
# column list is a safe subset to use on both sides of the INSERT.
# For tables that JOIN frames (ocr_text, elements), the SELECT side needs
# alias-qualified columns because both tables share names (app_name, etc).
FRAMES_COLS=$(build_col_list frames)
ELEMENTS_COLS=$(build_col_list elements)
ELEMENTS_COLS_E=$(build_col_list elements e)
UI_EVENTS_COLS=$(build_col_list ui_events)
OCR_TEXT_COLS=$(build_col_list ocr_text)
OCR_TEXT_COLS_O=$(build_col_list ocr_text o)
VIDEO_CHUNKS_COLS=$(build_col_list video_chunks)
MEETINGS_COLS=$(build_col_list meetings)
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks ($VIDEO_CHUNKS_COLS)
SELECT $VIDEO_CHUNKS_COLS FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames ($FRAMES_COLS)
SELECT $FRAMES_COLS FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text ($OCR_TEXT_COLS)
SELECT $OCR_TEXT_COLS_O FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events ($UI_EVENTS_COLS)
SELECT $UI_EVENTS_COLS FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements ($ELEMENTS_COLS)
SELECT $ELEMENTS_COLS_E FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings ($MEETINGS_COLS)
SELECT $MEETINGS_COLS FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
# Screenpipe writes daily logs to ~/.screenpipe/screenpipe.YYYY-MM-DD.N.log
# (N is a rotation counter, almost always 0). Mirror them to NAS so log
# analysis can happen on the consumer side without SSH'ing back to the Mac.
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
# Use a glob with nullglob so an empty match doesn't expand to a literal pattern.
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
# No --ignore-existing here: logs grow during the day, so we want rsync's
# default size+mtime check to refresh files that have changed.
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
COPIED=${#LOG_FILES[@]}
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "$COPIED" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
# Mirror this script's own logbook to NAS so sync health can be monitored
# from the consumer side. Done last so the summary lines above are included.
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 480, Col 3
git-commit Not Committed Yet
Not Committed Yet
No results found
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21104
|
|
21105
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Schema-drift tolerant: if Screenpipe migrations add new columns to the source DB,
# the NAS archive gets ALTER TABLE'd to match. Inserts use explicit column lists,
# so positional mismatches can't occur.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# Tables that get schema drift handling. Order matters for FK-ish references
# (parents before children: video_chunks → frames → elements/ocr_text/ui_events).
SYNC_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ─── SCHEMA HELPERS ───────────────────────────────────────────────────────────
# Echoes "name|type" lines for a table from a given DB.
table_columns_with_types() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2 "|" $3}'
}
# Echoes just column names, one per line.
table_columns() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2}'
}
# Returns true (0) if a table exists in the given DB.
table_exists() {
local db="$1" table="$2"
local count
count=$(sqlite3 "$db" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$table';")
[ "$count" -gt 0 ]
}
# Adds any columns present in source but missing in NAS for the given table.
# Uses ALTER TABLE ADD COLUMN, which is a fast metadata-only operation in SQLite.
ensure_columns() {
local table="$1"
local label="schema: $table"
printf " %-36s " "$label"
if ! table_exists "$DB_SRC" "$table"; then
printf "✗ source missing — skipping\n"
return 0
fi
if ! table_exists "$NAS_DB" "$table"; then
printf "✓ fresh (created above)\n"
return 0
fi
local src_cols
src_cols=$(table_columns_with_types "$DB_SRC" "$table")
local nas_cols
nas_cols=$(table_columns "$NAS_DB" "$table")
local added=0
local added_names=""
while IFS='|' read -r name type; do
[ -z "$name" ] && continue
# Use grep -F -x for fixed-string exact match (safe against regex chars).
if ! echo "$nas_cols" | grep -Fxq "$name"; then
# SQLite ALTER TABLE ADD COLUMN: type is optional, no NOT NULL allowed
# without a constant default. Default-NULL is exactly what we want for archive.
sqlite3 "$NAS_DB" "ALTER TABLE $table ADD COLUMN \"$name\" $type;"
added=$((added + 1))
added_names="$added_names $name"
fi
done <<< "$src_cols"
if [ "$added" -gt 0 ]; then
printf "✓ added %d:%s\n" "$added" "$added_names"
else
printf "✓ in sync\n"
fi
}
# Echoes a comma-separated list of source columns for a table, double-quoted
# so reserved words and hyphens are safe. If an alias is provided, columns are
# prefixed (e.g. `o."col"`). Used for both INSERT and SELECT sides; aliased
# form is required when SELECTing from a JOIN where column names collide
# (e.g. ocr_text and frames both have app_name, window_name).
build_col_list() {
local table="$1"
local alias="${2:-}"
local prefix=""
[ -n "$alias" ] && prefix="${alias}."
table_columns "$DB_SRC" "$table" | awk 'NF' | awk -v p="$prefix" '{print p "\"" $0 "\""}' | paste -sd, -
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
if table_exists "$NAS_DB" "frames"; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "exists, no frames table yet"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables (CREATE IF NOT EXISTS)"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
# ─── SCHEMA DRIFT FIX ─────────────────────────────────────────────────────
# Runs AFTER CREATE IF NOT EXISTS so newly-created tables are no-ops here,
# and pre-existing tables get any missing columns added.
step "Reconciling NAS schema with source"
for tbl in "${SYNC_TABLES[@]}"; do
ensure_columns "$tbl"
done
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_frames_document_path ON frames(document_path) WHERE document_path IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_onscreen_frame ON elements(frame_id) WHERE on_screen = 1 AND text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── BUILD EXPLICIT COLUMN LISTS ──────────────────────────────────────────
# After ensure_columns, source ⊆ NAS for every synced table, so source's
# column list is a safe subset to use on both sides of the INSERT.
# For tables that JOIN frames (ocr_text, elements), the SELECT side needs
# alias-qualified columns because both tables share names (app_name, etc).
FRAMES_COLS=$(build_col_list frames)
ELEMENTS_COLS=$(build_col_list elements)
ELEMENTS_COLS_E=$(build_col_list elements e)
UI_EVENTS_COLS=$(build_col_list ui_events)
OCR_TEXT_COLS=$(build_col_list ocr_text)
OCR_TEXT_COLS_O=$(build_col_list ocr_text o)
VIDEO_CHUNKS_COLS=$(build_col_list video_chunks)
MEETINGS_COLS=$(build_col_list meetings)
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks ($VIDEO_CHUNKS_COLS)
SELECT $VIDEO_CHUNKS_COLS FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames ($FRAMES_COLS)
SELECT $FRAMES_COLS FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text ($OCR_TEXT_COLS)
SELECT $OCR_TEXT_COLS_O FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events ($UI_EVENTS_COLS)
SELECT $UI_EVENTS_COLS FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements ($ELEMENTS_COLS)
SELECT $ELEMENTS_COLS_E FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings ($MEETINGS_COLS)
SELECT $MEETINGS_COLS FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
# Screenpipe writes daily logs to ~/.screenpipe/screenpipe.YYYY-MM-DD.N.log
# (N is a rotation counter, almost always 0). Mirror them to NAS so log
# analysis can happen on the consumer side without SSH'ing back to the Mac.
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
# Use a glob with nullglob so an empty match doesn't expand to a literal pattern.
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
# No --ignore-existing here: logs grow during the day, so we want rsync's
# default size+mtime check to refresh files that have changed.
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
COPIED=${#LOG_FILES[@]}
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "$COPIED" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
# Mirror this script's own logbook to NAS so sync health can be monitored
# from the consumer side. Done last so the summary lines above are included.
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Schema-drift tolerant: if Screenpipe migrations add new columns to the source DB,
# the NAS archive gets ALTER TABLE'd to match. Inserts use explicit column lists,
# so positional mismatches can't occur.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# Tables that get schema drift handling. Order matters for FK-ish references
# (parents before children: video_chunks → frames → elements/ocr_text/ui_events).
SYNC_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ─── SCHEMA HELPERS ───────────────────────────────────────────────────────────
# Echoes "name|type" lines for a table from a given DB.
table_columns_with_types() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2 "|" $3}'
}
# Echoes just column names, one per line.
table_columns() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2}'
}
# Returns true (0) if a table exists in the given DB.
table_exists() {
local db="$1" table="$2"
local count
count=$(sqlite3 "$db" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$table';")
[ "$count" -gt 0 ]
}
# Adds any columns present in source but missing in NAS for the given table.
# Uses ALTER TABLE ADD COLUMN, which is a fast metadata-only operation in SQLite.
ensure_columns() {
local table="$1"
local label="schema: $table"
printf " %-36s " "$label"
if ! table_exists "$DB_SRC" "$table"; then
printf "✗ source missing — skipping\n"
return 0
fi
if ! table_exists "$NAS_DB" "$table"; then
printf "✓ fresh (created above)\n"
return 0
fi
local src_cols
src_cols=$(table_columns_with_types "$DB_SRC" "$table")
local nas_cols
nas_cols=$(table_columns "$NAS_DB" "$table")
local added=0
local added_names=""
while IFS='|' read -r name type; do
[ -z "$name" ] && continue
# Use grep -F -x for fixed-string exact match (safe against regex chars).
if ! echo "$nas_cols" | grep -Fxq "$name"; then
# SQLite ALTER TABLE ADD COLUMN: type is optional, no NOT NULL allowed
# without a constant default. Default-NULL is exactly what we want for archive.
sqlite3 "$NAS_DB" "ALTER TABLE $table ADD COLUMN \"$name\" $type;"
added=$((added + 1))
added_names="$added_names $name"
fi
done <<< "$src_cols"
if [ "$added" -gt 0 ]; then
printf "✓ added %d:%s\n" "$added" "$added_names"
else
printf "✓ in sync\n"
fi
}
# Echoes a comma-separated list of source columns for a table, double-quoted
# so reserved words and hyphens are safe. If an alias is provided, columns are
# prefixed (e.g. `o."col"`). Used for both INSERT and SELECT sides; aliased
# form is required when SELECTing from a JOIN where column names collide
# (e.g. ocr_text and frames both have app_name, window_name).
build_col_list() {
local table="$1"
local alias="${2:-}"
local prefix=""
[ -n "$alias" ] && prefix="${alias}."
table_columns "$DB_SRC" "$table" | awk 'NF' | awk -v p="$prefix" '{print p "\"" $0 "\""}' | paste -sd, -
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
if table_exists "$NAS_DB" "frames"; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "exists, no frames table yet"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables (CREATE IF NOT EXISTS)"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
# ─── SCHEMA DRIFT FIX ─────────────────────────────────────────────────────
# Runs AFTER CREATE IF NOT EXISTS so newly-created tables are no-ops here,
# and pre-existing tables get any missing columns added.
step "Reconciling NAS schema with source"
for tbl in "${SYNC_TABLES[@]}"; do
ensure_columns "$tbl"
done
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_frames_document_path ON frames(document_path) WHERE document_path IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_onscreen_frame ON elements(frame_id) WHERE on_screen = 1 AND text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── BUILD EXPLICIT COLUMN LISTS ──────────────────────────────────────────
# After ensure_columns, source ⊆ NAS for every synced table, so source's
# column list is a safe subset to use on both sides of the INSERT.
# For tables that JOIN frames (ocr_text, elements), the SELECT side needs
# alias-qualified columns because both tables share names (app_name, etc).
FRAMES_COLS=$(build_col_list frames)
ELEMENTS_COLS=$(build_col_list elements)
ELEMENTS_COLS_E=$(build_col_list elements e)
UI_EVENTS_COLS=$(build_col_list ui_events)
OCR_TEXT_COLS=$(build_col_list ocr_text)
OCR_TEXT_COLS_O=$(build_col_list ocr_text o)
VIDEO_CHUNKS_COLS=$(build_col_list video_chunks)
MEETINGS_COLS=$(build_col_list meetings)
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks ($VIDEO_CHUNKS_COLS)
SELECT $VIDEO_CHUNKS_COLS FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames ($FRAMES_COLS)
SELECT $FRAMES_COLS FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text ($OCR_TEXT_COLS)
SELECT $OCR_TEXT_COLS_O FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events ($UI_EVENTS_COLS)
SELECT $UI_EVENTS_COLS FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements ($ELEMENTS_COLS)
SELECT $ELEMENTS_COLS_E FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings ($MEETINGS_COLS)
SELECT $MEETINGS_COLS FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
# Screenpipe writes daily logs to ~/.screenpipe/screenpipe.YYYY-MM-DD.N.log
# (N is a rotation counter, almost always 0). Mirror them to NAS so log
# analysis can happen on the consumer side without SSH'ing back to the Mac.
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
# Use a glob with nullglob so an empty match doesn't expand to a literal pattern.
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
# No --ignore-existing here: logs grow during the day, so we want rsync's
# default size+mtime check to refresh files that have changed.
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
COPIED=${#LOG_FILES[@]}
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "$COPIED" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
# Mirror this script's own logbook to NAS so sync health can be monitored
# from the consumer side. Done last so the summary lines above are included.
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 480, Col 3
git-commit Not Committed Yet...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21105
|
|
21106
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Schema-drift tolerant: if Screenpipe migrations add new columns to the source DB,
# the NAS archive gets ALTER TABLE'd to match. Inserts use explicit column lists,
# so positional mismatches can't occur.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# Tables that get schema drift handling. Order matters for FK-ish references
# (parents before children: video_chunks → frames → elements/ocr_text/ui_events).
SYNC_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ─── SCHEMA HELPERS ───────────────────────────────────────────────────────────
# Echoes "name|type" lines for a table from a given DB.
table_columns_with_types() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2 "|" $3}'
}
# Echoes just column names, one per line.
table_columns() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2}'
}
# Returns true (0) if a table exists in the given DB.
table_exists() {
local db="$1" table="$2"
local count
count=$(sqlite3 "$db" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$table';")
[ "$count" -gt 0 ]
}
# Adds any columns present in source but missing in NAS for the given table.
# Uses ALTER TABLE ADD COLUMN, which is a fast metadata-only operation in SQLite.
ensure_columns() {
local table="$1"
local label="schema: $table"
printf " %-36s " "$label"
if ! table_exists "$DB_SRC" "$table"; then
printf "✗ source missing — skipping\n"
return 0
fi
if ! table_exists "$NAS_DB" "$table"; then
printf "✓ fresh (created above)\n"
return 0
fi
local src_cols
src_cols=$(table_columns_with_types "$DB_SRC" "$table")
local nas_cols
nas_cols=$(table_columns "$NAS_DB" "$table")
local added=0
local added_names=""
while IFS='|' read -r name type; do
[ -z "$name" ] && continue
# Use grep -F -x for fixed-string exact match (safe against regex chars).
if ! echo "$nas_cols" | grep -Fxq "$name"; then
# SQLite ALTER TABLE ADD COLUMN: type is optional, no NOT NULL allowed
# without a constant default. Default-NULL is exactly what we want for archive.
sqlite3 "$NAS_DB" "ALTER TABLE $table ADD COLUMN \"$name\" $type;"
added=$((added + 1))
added_names="$added_names $name"
fi
done <<< "$src_cols"
if [ "$added" -gt 0 ]; then
printf "✓ added %d:%s\n" "$added" "$added_names"
else
printf "✓ in sync\n"
fi
}
# Echoes a comma-separated list of source columns for a table, double-quoted
# so reserved words and hyphens are safe. If an alias is provided, columns are
# prefixed (e.g. `o."col"`). Used for both INSERT and SELECT sides; aliased
# form is required when SELECTing from a JOIN where column names collide
# (e.g. ocr_text and frames both have app_name, window_name).
build_col_list() {
local table="$1"
local alias="${2:-}"
local prefix=""
[ -n "$alias" ] && prefix="${alias}."
table_columns "$DB_SRC" "$table" | awk 'NF' | awk -v p="$prefix" '{print p "\"" $0 "\""}' | paste -sd, -
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
if table_exists "$NAS_DB" "frames"; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "exists, no frames table yet"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables (CREATE IF NOT EXISTS)"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
# ─── SCHEMA DRIFT FIX ─────────────────────────────────────────────────────
# Runs AFTER CREATE IF NOT EXISTS so newly-created tables are no-ops here,
# and pre-existing tables get any missing columns added.
step "Reconciling NAS schema with source"
for tbl in "${SYNC_TABLES[@]}"; do
ensure_columns "$tbl"
done
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_frames_document_path ON frames(document_path) WHERE document_path IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_onscreen_frame ON elements(frame_id) WHERE on_screen = 1 AND text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── BUILD EXPLICIT COLUMN LISTS ──────────────────────────────────────────
# After ensure_columns, source ⊆ NAS for every synced table, so source's
# column list is a safe subset to use on both sides of the INSERT.
# For tables that JOIN frames (ocr_text, elements), the SELECT side needs
# alias-qualified columns because both tables share names (app_name, etc).
FRAMES_COLS=$(build_col_list frames)
ELEMENTS_COLS=$(build_col_list elements)
ELEMENTS_COLS_E=$(build_col_list elements e)
UI_EVENTS_COLS=$(build_col_list ui_events)
OCR_TEXT_COLS=$(build_col_list ocr_text)
OCR_TEXT_COLS_O=$(build_col_list ocr_text o)
VIDEO_CHUNKS_COLS=$(build_col_list video_chunks)
MEETINGS_COLS=$(build_col_list meetings)
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks ($VIDEO_CHUNKS_COLS)
SELECT $VIDEO_CHUNKS_COLS FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames ($FRAMES_COLS)
SELECT $FRAMES_COLS FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text ($OCR_TEXT_COLS)
SELECT $OCR_TEXT_COLS_O FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events ($UI_EVENTS_COLS)
SELECT $UI_EVENTS_COLS FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements ($ELEMENTS_COLS)
SELECT $ELEMENTS_COLS_E FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings ($MEETINGS_COLS)
SELECT $MEETINGS_COLS FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
# Screenpipe writes daily logs to ~/.screenpipe/screenpipe.YYYY-MM-DD.N.log
# (N is a rotation counter, almost always 0). Mirror them to NAS so log
# analysis can happen on the consumer side without SSH'ing back to the Mac.
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
# Use a glob with nullglob so an empty match doesn't expand to a literal pattern.
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
# No --ignore-existing here: logs grow during the day, so we want rsync's
# default size+mtime check to refresh files that have changed.
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
COPIED=${#LOG_FILES[@]}
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "$COPIED" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
# Mirror this script's own logbook to NAS so sync health can be monitored
# from the consumer side. Done last so the summary lines above are included.
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
#!/bin/bash
# screenpipe_sync.sh
# Syncs Screenpipe SQLite data to a NAS archive database (append-only, no deletions).
# Also copies the day's video/frame data folder to the NAS.
#
# Schema-drift tolerant: if Screenpipe migrations add new columns to the source DB,
# the NAS archive gets ALTER TABLE'd to match. Inserts use explicit column lists,
# so positional mismatches can't occur.
#
# Usage:
# ./screenpipe_sync.sh # syncs yesterday (default)
# ./screenpipe_sync.sh 2026-04-15 # syncs a specific date
# ./screenpipe_sync.sh today # syncs today so far
#
# Cron example (runs at 3am daily):
# 0 3 * * * /Users/lukas/.screenpipe/screenpipe_sync.sh >> /Users/lukas/.screenpipe/sync.log 2>&1
set -euo pipefail
# ─── CONFIG ───────────────────────────────────────────────────────────────────
DB_SRC="${SCREENPIPE_DB:-$HOME/.screenpipe/db.sqlite}"
NAS_MOUNT="${NAS_MOUNT:-/Volumes/screenpipe}"
NAS_DB="$NAS_MOUNT/archive.db"
NAS_DATA="$NAS_MOUNT/data"
LOG_FILE="$HOME/.screenpipe/sync.log"
# Tables that get schema drift handling. Order matters for FK-ish references
# (parents before children: video_chunks → frames → elements/ocr_text/ui_events).
SYNC_TABLES=(video_chunks frames elements ocr_text ui_events meetings)
# ──────────────────────────────────────────────────────────────────────────────
# ─── HELPERS ──────────────────────────────────────────────────────────────────
SCRIPT_START=$(date +%s)
log() {
local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
echo "$msg" | tee -a "$LOG_FILE"
}
step() {
local now=$(date +%s)
local elapsed=$(( now - SCRIPT_START ))
local min=$(( elapsed / 60 ))
local sec=$(( elapsed % 60 ))
printf "\n[+%02dm%02ds] ▶ %s\n" "$min" "$sec" "$*" | tee -a "$LOG_FILE"
}
run_sqlite_heredoc() {
local label="$1"
local sql="$2"
local start=$(date +%s)
printf " %-36s " "$label"
sqlite3 "$DB_SRC" <<< "$sql" &
local pid=$!
local spin=[PASSWORD] '⠙' '⠹' '⠸' '⠼' '⠴' '⠦' '⠧' '⠇' '⠏')
local i=0
while kill -0 "$pid" 2>/dev/null; do
printf "\r %-36s %s " "$label" "${spin[$i]}"
i=$(( (i + 1) % 10 ))
sleep 0.2
done
wait "$pid"
local rc=$?
if [ $rc -ne 0 ]; then
printf "\r %-36s ✗ FAILED\n" "$label" | tee -a "$LOG_FILE"
exit $rc
fi
local dur=$(( $(date +%s) - start ))
printf "\r %-36s ✓ %dm%02ds\n" "$label" "$(( dur / 60 ))" "$(( dur % 60 ))" | tee -a "$LOG_FILE"
}
check() {
local label="$1" got="$2" expected="$3"
if [ "$got" -eq "$expected" ]; then
printf " %-20s %s / %s ✓\n" "$label:" "$got" "$expected"
else
printf " %-20s %s / %s ✗ MISMATCH\n" "$label:" "$got" "$expected"
fi
}
# ─── SCHEMA HELPERS ───────────────────────────────────────────────────────────
# Echoes "name|type" lines for a table from a given DB.
table_columns_with_types() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2 "|" $3}'
}
# Echoes just column names, one per line.
table_columns() {
local db="$1" table="$2"
sqlite3 "$db" "PRAGMA table_info($table);" | awk -F'|' '{print $2}'
}
# Returns true (0) if a table exists in the given DB.
table_exists() {
local db="$1" table="$2"
local count
count=$(sqlite3 "$db" "SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='$table';")
[ "$count" -gt 0 ]
}
# Adds any columns present in source but missing in NAS for the given table.
# Uses ALTER TABLE ADD COLUMN, which is a fast metadata-only operation in SQLite.
ensure_columns() {
local table="$1"
local label="schema: $table"
printf " %-36s " "$label"
if ! table_exists "$DB_SRC" "$table"; then
printf "✗ source missing — skipping\n"
return 0
fi
if ! table_exists "$NAS_DB" "$table"; then
printf "✓ fresh (created above)\n"
return 0
fi
local src_cols
src_cols=$(table_columns_with_types "$DB_SRC" "$table")
local nas_cols
nas_cols=$(table_columns "$NAS_DB" "$table")
local added=0
local added_names=""
while IFS='|' read -r name type; do
[ -z "$name" ] && continue
# Use grep -F -x for fixed-string exact match (safe against regex chars).
if ! echo "$nas_cols" | grep -Fxq "$name"; then
# SQLite ALTER TABLE ADD COLUMN: type is optional, no NOT NULL allowed
# without a constant default. Default-NULL is exactly what we want for archive.
sqlite3 "$NAS_DB" "ALTER TABLE $table ADD COLUMN \"$name\" $type;"
added=$((added + 1))
added_names="$added_names $name"
fi
done <<< "$src_cols"
if [ "$added" -gt 0 ]; then
printf "✓ added %d:%s\n" "$added" "$added_names"
else
printf "✓ in sync\n"
fi
}
# Echoes a comma-separated list of source columns for a table, double-quoted
# so reserved words and hyphens are safe. If an alias is provided, columns are
# prefixed (e.g. `o."col"`). Used for both INSERT and SELECT sides; aliased
# form is required when SELECTing from a JOIN where column names collide
# (e.g. ocr_text and frames both have app_name, window_name).
build_col_list() {
local table="$1"
local alias="${2:-}"
local prefix=""
[ -n "$alias" ] && prefix="${alias}."
table_columns "$DB_SRC" "$table" | awk 'NF' | awk -v p="$prefix" '{print p "\"" $0 "\""}' | paste -sd, -
}
# ──────────────────────────────────────────────────────────────────────────────
# ─── DATE ARGUMENT ────────────────────────────────────────────────────────────
if [ "${1:-}" = "today" ]; then
TARGET_DATE=$(date +%Y-%m-%d)
elif [ -n "${1:-}" ]; then
TARGET_DATE="$1"
if ! [[ "$TARGET_DATE" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
echo "ERROR: Invalid date format. Use YYYY-MM-DD, 'today', or no argument for yesterday."
exit 1
fi
else
TARGET_DATE=$(date -v-1d +%Y-%m-%d)
fi
log "========================================"
log "Screenpipe sync starting for: $TARGET_DATE"
log "========================================"
# ─── PREFLIGHT ────────────────────────────────────────────────────────────────
step "Preflight checks"
if [ ! -f "$DB_SRC" ]; then
log "ERROR: Source DB not found at $DB_SRC"; exit 1
fi
printf " %-20s %s (%s)\n" "Source DB:" "OK" "$(du -sh "$DB_SRC" | cut -f1)"
if [ ! -d "$NAS_MOUNT" ]; then
log "ERROR: NAS not mounted at $NAS_MOUNT"; exit 1
fi
printf " %-20s %s\n" "NAS mount:" "OK $NAS_MOUNT"
# Check if DB already synced for this date
DB_ALREADY_SYNCED=false
if [ -f "$NAS_DB" ]; then
if table_exists "$NAS_DB" "frames"; then
EXISTING=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';" 2>/dev/null || echo "0")
if [ "$EXISTING" -gt "0" ]; then
log "Date $TARGET_DATE already has $EXISTING frames in archive — skipping DB sync"
DB_ALREADY_SYNCED=true
else
printf " %-20s %s (%s)\n" "Archive DB:" "exists" "$(du -sh "$NAS_DB" | cut -f1)"
fi
else
printf " %-20s %s\n" "Archive DB:" "exists, no frames table yet"
fi
else
printf " %-20s %s\n" "Archive DB:" "will be created"
fi
# Source data dir for this date
DATA_SRC="$HOME/.screenpipe/data/data/$TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
DATA_SIZE=$(du -sh "$DATA_SRC" | cut -f1)
DATA_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
printf " %-20s %s (%s files, %s)\n" "Data dir:" "OK" "$DATA_FILES" "$DATA_SIZE"
else
printf " %-20s %s\n" "Data dir:" "not found — skipping file copy"
fi
# ─── DB SYNC ──────────────────────────────────────────────────────────────────
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── COUNT SOURCE ROWS ────────────────────────────────────────────────────
step "Counting source rows for $TARGET_DATE"
SRC_FRAMES=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
SRC_ELEMENTS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_UI=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
SRC_OCR=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
SRC_MEETINGS=$(sqlite3 "$DB_SRC" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE';")
printf " %-20s %s\n" "frames:" "$SRC_FRAMES"
printf " %-20s %s\n" "elements:" "$SRC_ELEMENTS"
printf " %-20s %s\n" "ui_events:" "$SRC_UI"
printf " %-20s %s\n" "ocr_text:" "$SRC_OCR"
printf " %-20s %s\n" "meetings:" "$SRC_MEETINGS"
if [ "$SRC_FRAMES" -eq "0" ]; then
log "No frames found for $TARGET_DATE — skipping DB sync"
DB_ALREADY_SYNCED=true
fi
fi
if [ "$DB_ALREADY_SYNCED" = false ]; then
# ─── INIT TABLES ──────────────────────────────────────────────────────────
step "Initialising tables (CREATE IF NOT EXISTS)"
run_sqlite_heredoc "creating tables" "
ATTACH '$NAS_DB' AS nas;
CREATE TABLE IF NOT EXISTS nas.frames AS SELECT * FROM main.frames WHERE 0;
CREATE TABLE IF NOT EXISTS nas.elements AS SELECT * FROM main.elements WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ui_events AS SELECT * FROM main.ui_events WHERE 0;
CREATE TABLE IF NOT EXISTS nas.ocr_text AS SELECT * FROM main.ocr_text WHERE 0;
CREATE TABLE IF NOT EXISTS nas.video_chunks AS SELECT * FROM main.video_chunks WHERE 0;
CREATE TABLE IF NOT EXISTS nas.meetings AS SELECT * FROM main.meetings WHERE 0;
DETACH nas;
"
# ─── SCHEMA DRIFT FIX ─────────────────────────────────────────────────────
# Runs AFTER CREATE IF NOT EXISTS so newly-created tables are no-ops here,
# and pre-existing tables get any missing columns added.
step "Reconciling NAS schema with source"
for tbl in "${SYNC_TABLES[@]}"; do
ensure_columns "$tbl"
done
run_sqlite_heredoc "creating indexes" "
ATTACH '$NAS_DB' AS nas;
CREATE INDEX IF NOT EXISTS nas.idx_frames_timestamp ON frames(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_frames_app_name ON frames(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_window_name ON frames(window_name);
CREATE INDEX IF NOT EXISTS nas.idx_frames_video_chunk_id ON frames(video_chunk_id);
CREATE INDEX IF NOT EXISTS nas.idx_frames_document_path ON frames(document_path) WHERE document_path IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_id ON elements(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_elements_frame_src_role ON elements(frame_id, source, role) WHERE text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_elements_onscreen_frame ON elements(frame_id) WHERE on_screen = 1 AND text IS NOT NULL;
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_timestamp ON ui_events(timestamp);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_app_name ON ui_events(app_name);
CREATE INDEX IF NOT EXISTS nas.idx_ui_events_frame_id ON ui_events(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_ocr_text_frame_id ON ocr_text(frame_id);
CREATE INDEX IF NOT EXISTS nas.idx_meetings_start ON meetings(meeting_start);
CREATE INDEX IF NOT EXISTS nas.idx_video_chunks_device ON video_chunks(device_name);
DETACH nas;
"
run_sqlite_heredoc "creating FTS tables" "
ATTACH '$NAS_DB' AS nas;
CREATE VIRTUAL TABLE IF NOT EXISTS nas.elements_fts USING fts5(
text, role, frame_id UNINDEXED,
content='elements', content_rowid='id', tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.frames_fts USING fts5(
full_text, app_name, window_name, browser_url, id UNINDEXED,
tokenize='unicode61'
);
CREATE VIRTUAL TABLE IF NOT EXISTS nas.ui_events_fts USING fts5(
text_content,
app_name,
window_title,
element_name,
content='ui_events',
content_rowid='id',
tokenize='unicode61'
);
DETACH nas;
"
# ─── BUILD EXPLICIT COLUMN LISTS ──────────────────────────────────────────
# After ensure_columns, source ⊆ NAS for every synced table, so source's
# column list is a safe subset to use on both sides of the INSERT.
# For tables that JOIN frames (ocr_text, elements), the SELECT side needs
# alias-qualified columns because both tables share names (app_name, etc).
FRAMES_COLS=$(build_col_list frames)
ELEMENTS_COLS=$(build_col_list elements)
ELEMENTS_COLS_E=$(build_col_list elements e)
UI_EVENTS_COLS=$(build_col_list ui_events)
OCR_TEXT_COLS=$(build_col_list ocr_text)
OCR_TEXT_COLS_O=$(build_col_list ocr_text o)
VIDEO_CHUNKS_COLS=$(build_col_list video_chunks)
MEETINGS_COLS=$(build_col_list meetings)
# ─── SYNC DATA ────────────────────────────────────────────────────────────
step "Syncing data for $TARGET_DATE"
run_sqlite_heredoc "video_chunks" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.video_chunks ($VIDEO_CHUNKS_COLS)
SELECT $VIDEO_CHUNKS_COLS FROM main.video_chunks
WHERE id IN (
SELECT DISTINCT video_chunk_id FROM main.frames
WHERE date(timestamp) = '$TARGET_DATE' AND video_chunk_id IS NOT NULL
);
DETACH nas;
"
run_sqlite_heredoc "frames ($SRC_FRAMES rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames ($FRAMES_COLS)
SELECT $FRAMES_COLS FROM main.frames WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ocr_text ($SRC_OCR rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ocr_text ($OCR_TEXT_COLS)
SELECT $OCR_TEXT_COLS_O FROM main.ocr_text o
JOIN main.frames f ON o.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "ui_events ($SRC_UI rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events ($UI_EVENTS_COLS)
SELECT $UI_EVENTS_COLS FROM main.ui_events WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "elements ($SRC_ELEMENTS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements ($ELEMENTS_COLS)
SELECT $ELEMENTS_COLS_E FROM main.elements e
JOIN main.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "meetings ($SRC_MEETINGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.meetings ($MEETINGS_COLS)
SELECT $MEETINGS_COLS FROM main.meetings WHERE date(meeting_start) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND text_content IS NOT NULL;
DETACH nas;
"
# ─── VERIFY DB ────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start)= '$TARGET_DATE';")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
fi
# ─── COPY DATA FOLDER ─────────────────────────────────────────────────────────
# Always runs regardless of DB sync status
step "Copying data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync $TARGET_DATE/ → NAS"
rsync -a --ignore-existing \
"$DATA_SRC/" \
"$NAS_DATA/$TARGET_DATE/" \
2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -eq "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync $TARGET_DATE/ → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync $TARGET_DATE/ → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync $TARGET_DATE/ → NAS" "skipped (no source dir)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
# Screenpipe writes daily logs to ~/.screenpipe/screenpipe.YYYY-MM-DD.N.log
# (N is a rotation counter, almost always 0). Mirror them to NAS so log
# analysis can happen on the consumer side without SSH'ing back to the Mac.
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
# Use a glob with nullglob so an empty match doesn't expand to a literal pattern.
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
# No --ignore-existing here: logs grow during the day, so we want rsync's
# default size+mtime check to refresh files that have changed.
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
COPIED=${#LOG_FILES[@]}
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "$COPIED" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE"
log "========================================"
# Mirror this script's own logbook to NAS so sync health can be monitored
# from the consumer side. Done last so the summary lines above are included.
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21106
|
|
21107
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21107
|
|
21108
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21108
|
|
21109
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21109
|
|
21403
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21403
|
|
21405
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
# the source currently has; INSERT OR IGNORE handles the duplicate case.
run_sqlite_heredoc "speakers ($SRC_SPEAKERS rows, all-time)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.speakers ($SPEAKERS_COLS, install_id)
SELECT $SPEAKERS_COLS, '$INSTALL_ID' FROM main.speakers;
DETACH nas;
"
run_sqlite_heredoc "speaker_embeddings ($SRC_SEMB rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.speaker_embeddings ($SEMB_COLS, install_id)
SELECT $SEMB_COLS, '$INSTALL_ID' FROM main.speaker_embeddings;
DETACH nas;
"
run_sqlite_heredoc "audio_chunks ($SRC_ACHUNKS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_chunks ($ACHUNKS_COLS, install_id)
SELECT $ACHUNKS_COLS, '$INSTALL_ID' FROM main.audio_chunks WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "audio_transcriptions ($SRC_ATRANS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_transcriptions ($ATRANS_COLS, install_id)
SELECT $ATRANS_COLS_T, '$INSTALL_ID' FROM main.audio_transcriptions t
JOIN main.audio_chunks c ON t.audio_chunk_id = c.id
WHERE date(c.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "audio_tags ($SRC_ATAGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_tags ($ATAGS_COLS, install_id)
SELECT $ATAGS_COLS_AT, '$INSTALL_ID' FROM main.audio_tags at
JOIN main.audio_chunks c ON at.audio_chunk_id = c.id
WHERE date(c.timestamp) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id AND e.install_id = f.install_id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.install_id = '$INSTALL_ID'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND install_id = '$INSTALL_ID'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND install_id = '$INSTALL_ID'
AND text_content IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "audio_transcriptions_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_transcriptions_fts(rowid, transcription, device, speaker_id, id)
SELECT t.id, t.transcription, COALESCE(t.device,''), t.speaker_id, t.id
FROM nas.audio_transcriptions t
JOIN nas.audio_chunks c ON t.audio_chunk_id = c.id AND t.install_id = c.install_id
WHERE date(c.timestamp) = '$TARGET_DATE'
AND t.install_id = '$INSTALL_ID'
AND t.transcription IS NOT NULL AND t.transcription != '';
DETACH nas;
"
# ─── VERIFY ───────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE install_id='$INSTALL_ID' AND frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE install_id='$INSTALL_ID' AND frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ACHUNKS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ATRANS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_transcriptions WHERE install_id='$INSTALL_ID' AND audio_chunk_id IN (SELECT id FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_ATAGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_tags WHERE install_id='$INSTALL_ID' AND audio_chunk_id IN (SELECT id FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
check "audio_chunks" "$V_ACHUNKS" "$SRC_ACHUNKS"
check "audio_transcriptions" "$V_ATRANS" "$SRC_ATRANS"
check "audio_tags" "$V_ATAGS" "$SRC_ATAGS"
fi
# ─── COPY FRAME DATA FOLDER ──────────────────────────────────────────────────
# Always runs regardless of DB sync status.
step "Copying frame data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync frames → NAS"
rsync -a --ignore-existing "$DATA_SRC/" "$NAS_DATA/$TARGET_DATE/" 2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" 2>/dev/null | grep -v '^audio$' | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -ge "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync frames → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync frames → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync frames → NAS" "skipped (no source dir)"
fi
# ─── COPY AUDIO FILES ────────────────────────────────────────────────────────
# Audio is flat in ~/.screenpipe/data/ with the date in the filename, e.g.
# System Audio (output)_2026-05-11_13-48-12.mp4
# soundcore AeroClip (input)_2026-05-10_11-10-32.mp4
# Mirrored to $NAS_DATA/<date>/audio/ so each day's archive is self-contained.
step "Copying audio files for $TARGET_DATE"
shopt -s nullglob
AUDIO_FILES=( "$HOME/.screenpipe/data/"*_"${TARGET_DATE}"_*.mp4 )
shopt -u nullglob
if [ ${#AUDIO_FILES[@]} -gt 0 ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE/audio"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync audio → NAS"
rsync -a --ignore-existing "${AUDIO_FILES[@]}" "$NAS_DATA/$TARGET_DATE/audio/" 2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_AUDIO=$(ls "$NAS_DATA/$TARGET_DATE/audio" | wc -l | tr -d ' ')
AUDIO_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE/audio" | cut -f1)
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync audio → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_AUDIO" "$AUDIO_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync audio → NAS" "skipped (no audio for date)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "${#LOG_FILES[@]}" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE (install $INSTALL_ID)"
log "========================================"
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
# the source currently has; INSERT OR IGNORE handles the duplicate case.
run_sqlite_heredoc "speakers ($SRC_SPEAKERS rows, all-time)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.speakers ($SPEAKERS_COLS, install_id)
SELECT $SPEAKERS_COLS, '$INSTALL_ID' FROM main.speakers;
DETACH nas;
"
run_sqlite_heredoc "speaker_embeddings ($SRC_SEMB rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.speaker_embeddings ($SEMB_COLS, install_id)
SELECT $SEMB_COLS, '$INSTALL_ID' FROM main.speaker_embeddings;
DETACH nas;
"
run_sqlite_heredoc "audio_chunks ($SRC_ACHUNKS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_chunks ($ACHUNKS_COLS, install_id)
SELECT $ACHUNKS_COLS, '$INSTALL_ID' FROM main.audio_chunks WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "audio_transcriptions ($SRC_ATRANS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_transcriptions ($ATRANS_COLS, install_id)
SELECT $ATRANS_COLS_T, '$INSTALL_ID' FROM main.audio_transcriptions t
JOIN main.audio_chunks c ON t.audio_chunk_id = c.id
WHERE date(c.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "audio_tags ($SRC_ATAGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_tags ($ATAGS_COLS, install_id)
SELECT $ATAGS_COLS_AT, '$INSTALL_ID' FROM main.audio_tags at
JOIN main.audio_chunks c ON at.audio_chunk_id = c.id
WHERE date(c.timestamp) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id AND e.install_id = f.install_id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.install_id = '$INSTALL_ID'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND install_id = '$INSTALL_ID'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND install_id = '$INSTALL_ID'
AND text_content IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "audio_transcriptions_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_transcriptions_fts(rowid, transcription, device, speaker_id, id)
SELECT t.id, t.transcription, COALESCE(t.device,''), t.speaker_id, t.id
FROM nas.audio_transcriptions t
JOIN nas.audio_chunks c ON t.audio_chunk_id = c.id AND t.install_id = c.install_id
WHERE date(c.timestamp) = '$TARGET_DATE'
AND t.install_id = '$INSTALL_ID'
AND t.transcription IS NOT NULL AND t.transcription != '';
DETACH nas;
"
# ─── VERIFY ───────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE install_id='$INSTALL_ID' AND frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE install_id='$INSTALL_ID' AND frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ACHUNKS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ATRANS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_transcriptions WHERE install_id='$INSTALL_ID' AND audio_chunk_id IN (SELECT id FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_ATAGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_tags WHERE install_id='$INSTALL_ID' AND audio_chunk_id IN (SELECT id FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
check "audio_chunks" "$V_ACHUNKS" "$SRC_ACHUNKS"
check "audio_transcriptions" "$V_ATRANS" "$SRC_ATRANS"
check "audio_tags" "$V_ATAGS" "$SRC_ATAGS"
fi
# ─── COPY FRAME DATA FOLDER ──────────────────────────────────────────────────
# Always runs regardless of DB sync status.
step "Copying frame data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync frames → NAS"
rsync -a --ignore-existing "$DATA_SRC/" "$NAS_DATA/$TARGET_DATE/" 2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" 2>/dev/null | grep -v '^audio$' | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -ge "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync frames → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync frames → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync frames → NAS" "skipped (no source dir)"
fi
# ─── COPY AUDIO FILES ────────────────────────────────────────────────────────
# Audio is flat in ~/.screenpipe/data/ with the date in the filename, e.g.
# System Audio (output)_2026-05-11_13-48-12.mp4
# soundcore AeroClip (input)_2026-05-10_11-10-32.mp4
# Mirrored to $NAS_DATA/<date>/audio/ so each day's archive is self-contained.
step "Copying audio files for $TARGET_DATE"
shopt -s nullglob
AUDIO_FILES=( "$HOME/.screenpipe/data/"*_"${TARGET_DATE}"_*.mp4 )
shopt -u nullglob
if [ ${#AUDIO_FILES[@]} -gt 0 ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE/audio"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync audio → NAS"
rsync -a --ignore-existing "${AUDIO_FILES[@]}" "$NAS_DATA/$TARGET_DATE/audio/" 2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_AUDIO=$(ls "$NAS_DATA/$TARGET_DATE/audio" | wc -l | tr -d ' ')
AUDIO_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE/audio" | cut -f1)
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync audio → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_AUDIO" "$AUDIO_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync audio → NAS" "skipped (no audio for date)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "${#LOG_FILES[@]}" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE (install $INSTALL_ID)"
log "========================================"
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 675, Col 1
git-commit Not Committed Yet
Not Committed Yet
No results found
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:
Edit
main.py
main.py
Added 1 line
Edit
main.py
main.py
Added 1 line...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21405
|
|
21406
|
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Explorer (⇧⌘E) - 1 unsaved file
1
Search (⇧⌘F)
Source Control (⌃⇧G) - 10 pending changes
10
Run and Debug (⇧⌘D)
Remote Explorer
Extensions (⇧⌘X) - 2 require update
2
Claude Code
Containers
EXPLORER
EXPLORER
Explorer Section: screenpipe [SSH: nas]
Explorer Section: screenpipe [SSH: nas]
SCREENPIPE [SSH: NAS]
#recycle
app
__pycache__
consumers
static
.env
cli.py
M
db.py
docker-compose.yml
Dockerfile
M
main.py
M
requirements.txt
M
data
logs
pipes
.gitignore
app_settings.json
archive.db
archive.db-bak
U
db.sqlite
db.sqlite-shm
db.sqlite-wal
screenpipe_sync_updated.sh
U
screenpipe_sync.sh
screenpipe.db
Outline Section
OUTLINE
OUTLINE
Timeline Section
TIMELINE
TIMELINE
app_settings.json, Editor Group 1
screenpipe_sync.sh, Editor Group 1
screenpipe_sync_updated.sh, preview, Editor Group 1
pipe.md, Editor Group 1
.env, Editor Group 1
# the source currently has; INSERT OR IGNORE handles the duplicate case.
run_sqlite_heredoc "speakers ($SRC_SPEAKERS rows, all-time)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.speakers ($SPEAKERS_COLS, install_id)
SELECT $SPEAKERS_COLS, '$INSTALL_ID' FROM main.speakers;
DETACH nas;
"
run_sqlite_heredoc "speaker_embeddings ($SRC_SEMB rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.speaker_embeddings ($SEMB_COLS, install_id)
SELECT $SEMB_COLS, '$INSTALL_ID' FROM main.speaker_embeddings;
DETACH nas;
"
run_sqlite_heredoc "audio_chunks ($SRC_ACHUNKS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_chunks ($ACHUNKS_COLS, install_id)
SELECT $ACHUNKS_COLS, '$INSTALL_ID' FROM main.audio_chunks WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "audio_transcriptions ($SRC_ATRANS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_transcriptions ($ATRANS_COLS, install_id)
SELECT $ATRANS_COLS_T, '$INSTALL_ID' FROM main.audio_transcriptions t
JOIN main.audio_chunks c ON t.audio_chunk_id = c.id
WHERE date(c.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "audio_tags ($SRC_ATAGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_tags ($ATAGS_COLS, install_id)
SELECT $ATAGS_COLS_AT, '$INSTALL_ID' FROM main.audio_tags at
JOIN main.audio_chunks c ON at.audio_chunk_id = c.id
WHERE date(c.timestamp) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id AND e.install_id = f.install_id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.install_id = '$INSTALL_ID'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND install_id = '$INSTALL_ID'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND install_id = '$INSTALL_ID'
AND text_content IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "audio_transcriptions_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_transcriptions_fts(rowid, transcription, device, speaker_id, id)
SELECT t.id, t.transcription, COALESCE(t.device,''), t.speaker_id, t.id
FROM nas.audio_transcriptions t
JOIN nas.audio_chunks c ON t.audio_chunk_id = c.id AND t.install_id = c.install_id
WHERE date(c.timestamp) = '$TARGET_DATE'
AND t.install_id = '$INSTALL_ID'
AND t.transcription IS NOT NULL AND t.transcription != '';
DETACH nas;
"
# ─── VERIFY ───────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE install_id='$INSTALL_ID' AND frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE install_id='$INSTALL_ID' AND frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ACHUNKS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ATRANS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_transcriptions WHERE install_id='$INSTALL_ID' AND audio_chunk_id IN (SELECT id FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_ATAGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_tags WHERE install_id='$INSTALL_ID' AND audio_chunk_id IN (SELECT id FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
check "audio_chunks" "$V_ACHUNKS" "$SRC_ACHUNKS"
check "audio_transcriptions" "$V_ATRANS" "$SRC_ATRANS"
check "audio_tags" "$V_ATAGS" "$SRC_ATAGS"
fi
# ─── COPY FRAME DATA FOLDER ──────────────────────────────────────────────────
# Always runs regardless of DB sync status.
step "Copying frame data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync frames → NAS"
rsync -a --ignore-existing "$DATA_SRC/" "$NAS_DATA/$TARGET_DATE/" 2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" 2>/dev/null | grep -v '^audio$' | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -ge "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync frames → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync frames → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync frames → NAS" "skipped (no source dir)"
fi
# ─── COPY AUDIO FILES ────────────────────────────────────────────────────────
# Audio is flat in ~/.screenpipe/data/ with the date in the filename, e.g.
# System Audio (output)_2026-05-11_13-48-12.mp4
# soundcore AeroClip (input)_2026-05-10_11-10-32.mp4
# Mirrored to $NAS_DATA/<date>/audio/ so each day's archive is self-contained.
step "Copying audio files for $TARGET_DATE"
shopt -s nullglob
AUDIO_FILES=( "$HOME/.screenpipe/data/"*_"${TARGET_DATE}"_*.mp4 )
shopt -u nullglob
if [ ${#AUDIO_FILES[@]} -gt 0 ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE/audio"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync audio → NAS"
rsync -a --ignore-existing "${AUDIO_FILES[@]}" "$NAS_DATA/$TARGET_DATE/audio/" 2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_AUDIO=$(ls "$NAS_DATA/$TARGET_DATE/audio" | wc -l | tr -d ' ')
AUDIO_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE/audio" | cut -f1)
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync audio → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_AUDIO" "$AUDIO_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync audio → NAS" "skipped (no audio for date)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "${#LOG_FILES[@]}" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE (install $INSTALL_ID)"
log "========================================"
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
# the source currently has; INSERT OR IGNORE handles the duplicate case.
run_sqlite_heredoc "speakers ($SRC_SPEAKERS rows, all-time)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.speakers ($SPEAKERS_COLS, install_id)
SELECT $SPEAKERS_COLS, '$INSTALL_ID' FROM main.speakers;
DETACH nas;
"
run_sqlite_heredoc "speaker_embeddings ($SRC_SEMB rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.speaker_embeddings ($SEMB_COLS, install_id)
SELECT $SEMB_COLS, '$INSTALL_ID' FROM main.speaker_embeddings;
DETACH nas;
"
run_sqlite_heredoc "audio_chunks ($SRC_ACHUNKS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_chunks ($ACHUNKS_COLS, install_id)
SELECT $ACHUNKS_COLS, '$INSTALL_ID' FROM main.audio_chunks WHERE date(timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "audio_transcriptions ($SRC_ATRANS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_transcriptions ($ATRANS_COLS, install_id)
SELECT $ATRANS_COLS_T, '$INSTALL_ID' FROM main.audio_transcriptions t
JOIN main.audio_chunks c ON t.audio_chunk_id = c.id
WHERE date(c.timestamp) = '$TARGET_DATE';
DETACH nas;
"
run_sqlite_heredoc "audio_tags ($SRC_ATAGS rows)" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_tags ($ATAGS_COLS, install_id)
SELECT $ATAGS_COLS_AT, '$INSTALL_ID' FROM main.audio_tags at
JOIN main.audio_chunks c ON at.audio_chunk_id = c.id
WHERE date(c.timestamp) = '$TARGET_DATE';
DETACH nas;
"
# ─── FTS UPDATE ───────────────────────────────────────────────────────────
step "Updating FTS indexes"
run_sqlite_heredoc "elements_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.elements_fts(rowid, text, role)
SELECT e.id, e.text, e.role
FROM nas.elements e
JOIN nas.frames f ON e.frame_id = f.id AND e.install_id = f.install_id
WHERE date(f.timestamp) = '$TARGET_DATE'
AND e.install_id = '$INSTALL_ID'
AND e.text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "frames_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.frames_fts(rowid, full_text, app_name, window_name, browser_url, id)
SELECT id, full_text, app_name, window_name, browser_url, id
FROM nas.frames
WHERE date(timestamp) = '$TARGET_DATE'
AND install_id = '$INSTALL_ID'
AND full_text IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "ui_events_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.ui_events_fts(rowid, text_content, app_name, window_title, element_name)
SELECT id, text_content, app_name, window_title, element_name
FROM nas.ui_events
WHERE date(timestamp) = '$TARGET_DATE'
AND install_id = '$INSTALL_ID'
AND text_content IS NOT NULL;
DETACH nas;
"
run_sqlite_heredoc "audio_transcriptions_fts" "
ATTACH '$NAS_DB' AS nas;
INSERT OR IGNORE INTO nas.audio_transcriptions_fts(rowid, transcription, device, speaker_id, id)
SELECT t.id, t.transcription, COALESCE(t.device,''), t.speaker_id, t.id
FROM nas.audio_transcriptions t
JOIN nas.audio_chunks c ON t.audio_chunk_id = c.id AND t.install_id = c.install_id
WHERE date(c.timestamp) = '$TARGET_DATE'
AND t.install_id = '$INSTALL_ID'
AND t.transcription IS NOT NULL AND t.transcription != '';
DETACH nas;
"
# ─── VERIFY ───────────────────────────────────────────────────────────────
step "Verifying DB"
V_FRAMES=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ELEMENTS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM elements WHERE install_id='$INSTALL_ID' AND frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_UI=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ui_events WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_OCR=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM ocr_text WHERE install_id='$INSTALL_ID' AND frame_id IN (SELECT id FROM frames WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_MEETINGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM meetings WHERE date(meeting_start) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ACHUNKS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID';")
V_ATRANS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_transcriptions WHERE install_id='$INSTALL_ID' AND audio_chunk_id IN (SELECT id FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
V_ATAGS=$(sqlite3 "$NAS_DB" "SELECT COUNT(*) FROM audio_tags WHERE install_id='$INSTALL_ID' AND audio_chunk_id IN (SELECT id FROM audio_chunks WHERE date(timestamp) = '$TARGET_DATE' AND install_id='$INSTALL_ID');")
check "frames" "$V_FRAMES" "$SRC_FRAMES"
check "elements" "$V_ELEMENTS" "$SRC_ELEMENTS"
check "ui_events" "$V_UI" "$SRC_UI"
check "ocr_text" "$V_OCR" "$SRC_OCR"
check "meetings" "$V_MEETINGS" "$SRC_MEETINGS"
check "audio_chunks" "$V_ACHUNKS" "$SRC_ACHUNKS"
check "audio_transcriptions" "$V_ATRANS" "$SRC_ATRANS"
check "audio_tags" "$V_ATAGS" "$SRC_ATAGS"
fi
# ─── COPY FRAME DATA FOLDER ──────────────────────────────────────────────────
# Always runs regardless of DB sync status.
step "Copying frame data folder for $TARGET_DATE"
if [ -d "$DATA_SRC" ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync frames → NAS"
rsync -a --ignore-existing "$DATA_SRC/" "$NAS_DATA/$TARGET_DATE/" 2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_FILES=$(ls "$NAS_DATA/$TARGET_DATE" 2>/dev/null | grep -v '^audio$' | wc -l | tr -d ' ')
SRC_FILES=$(ls "$DATA_SRC" | wc -l | tr -d ' ')
COPIED_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE" | cut -f1)
if [ "$COPIED_FILES" -ge "$SRC_FILES" ]; then
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync frames → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_FILES" "$COPIED_SIZE" | tee -a "$LOG_FILE"
else
printf "\r %-36s ✗ %s / %s files\n" \
"rsync frames → NAS" "$COPIED_FILES" "$SRC_FILES" | tee -a "$LOG_FILE"
fi
else
printf " %-36s %s\n" "rsync frames → NAS" "skipped (no source dir)"
fi
# ─── COPY AUDIO FILES ────────────────────────────────────────────────────────
# Audio is flat in ~/.screenpipe/data/ with the date in the filename, e.g.
# System Audio (output)_2026-05-11_13-48-12.mp4
# soundcore AeroClip (input)_2026-05-10_11-10-32.mp4
# Mirrored to $NAS_DATA/<date>/audio/ so each day's archive is self-contained.
step "Copying audio files for $TARGET_DATE"
shopt -s nullglob
AUDIO_FILES=( "$HOME/.screenpipe/data/"*_"${TARGET_DATE}"_*.mp4 )
shopt -u nullglob
if [ ${#AUDIO_FILES[@]} -gt 0 ]; then
mkdir -p "$NAS_DATA/$TARGET_DATE/audio"
RSYNC_START=$(date +%s)
printf " %-36s " "rsync audio → NAS"
rsync -a --ignore-existing "${AUDIO_FILES[@]}" "$NAS_DATA/$TARGET_DATE/audio/" 2>>"$LOG_FILE"
RSYNC_DUR=$(( $(date +%s) - RSYNC_START ))
COPIED_AUDIO=$(ls "$NAS_DATA/$TARGET_DATE/audio" | wc -l | tr -d ' ')
AUDIO_SIZE=$(du -sh "$NAS_DATA/$TARGET_DATE/audio" | cut -f1)
printf "\r %-36s ✓ %dm%02ds (%s files, %s)\n" \
"rsync audio → NAS" \
"$(( RSYNC_DUR / 60 ))" "$(( RSYNC_DUR % 60 ))" \
"$COPIED_AUDIO" "$AUDIO_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync audio → NAS" "skipped (no audio for date)"
fi
# ─── COPY LOGS ────────────────────────────────────────────────────────────────
step "Copying screenpipe logs for $TARGET_DATE"
NAS_LOGS="$NAS_MOUNT/logs"
mkdir -p "$NAS_LOGS"
shopt -s nullglob
LOG_FILES=( "$HOME/.screenpipe/screenpipe.$TARGET_DATE."*.log )
shopt -u nullglob
if [ ${#LOG_FILES[@]} -gt 0 ]; then
printf " %-36s " "rsync logs → NAS"
rsync -a "${LOG_FILES[@]}" "$NAS_LOGS/" 2>>"$LOG_FILE"
TOTAL_SIZE=$(du -ch "${LOG_FILES[@]}" | tail -1 | cut -f1)
printf "✓ %d file(s), %s\n" "${#LOG_FILES[@]}" "$TOTAL_SIZE" | tee -a "$LOG_FILE"
else
printf " %-36s %s\n" "rsync logs → NAS" "skipped (no matching logs)"
fi
# ─── SUMMARY ──────────────────────────────────────────────────────────────────
TOTAL_ELAPSED=$(( $(date +%s) - SCRIPT_START ))
DB_SIZE=$(du -sh "$NAS_DB" | cut -f1)
echo ""
log "Archive DB size: $DB_SIZE"
log "Total time: $(( TOTAL_ELAPSED / 60 ))m$(( TOTAL_ELAPSED % 60 ))s"
log "Sync complete for $TARGET_DATE (install $INSTALL_ID)"
log "========================================"
rsync -a "$HOME/.screenpipe/sync.log" "$NAS_LOGS/sync.log" 2>/dev/null || true
Implement and run pipe l…, Editor Group 2
Problems (⇧⌘M)
PROBLEMS
Output (⇧⌘U)
OUTPUT
Debug Console (⇧⌘Y)
DEBUG CONSOLE
Terminal (⌃`)
TERMINAL
Ports - 1 forwarded port
PORTS
1
remote SSH: nas
SSH: nas
screenpipe (Git) - master*, Checkout Branch/Tag...
master*
screenpipe (Git) - Synchronize Changes
No Problems
0
0
Forwarded Ports: 8766
1
Notifications
Sign In
Sign In
Shell Script
Editor Language Status: Inline Suggestions, next: $(copilot) No inline suggestion available, Inline suggestions
LF
UTF-8
Spaces: 2
Ln 675, Col 1
git-commit Not Committed Yet
Not Committed Yet
No results found
Implement and run pipe logic
Session history
New session
Message actions
main.py
main.py
lets implement logic with pipes. how can I run it?
Thinking
Thinking
Let me look at the current project structure to understand what's already in place.
Bash
List project files
IN
find /volume1/screenpipe -type f | head -50 && echo "---" && ls /volume1/screenpipe
Copy code to clipboard
OUT
/volume1/screenpipe/.DS_Store
/volume1/screenpipe/screenpipe.db
/volume1/screenpipe/screenpipe_sync.sh
/volume1/screenpipe/app_settings.json
/volume1/screenpipe/.gitignore
/volume1/screenpipe/archive.db
/volume1/screenpipe/db.sqlite
/volume1/screenpipe/db.sqlite-wal
/volume1/screenpipe/db.sqlite-shm
/volume1/screenpipe/#recycle/desktop.ini
/volume1/screenpipe/#recycle/db.sqlite
/volume1/screenpipe/#recycle/Copy #1 of db.sqlite
/volume1/screenpipe/#recycle/.DS_Store
/volume1/screenpipe/#recycle/Copy #2 of db.sqlite
/volume1/screenpipe/#recycle/archive.db
/volume1/screenpipe/#recycle/Copy #1 of archive.db
/volume1/screenpipe/#recycle/Copy #2 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of archive.db
/volume1/screenpipe/#recycle/Copy #4 of archive.db
/volume1/screenpipe/#recycle/Copy #5 of archive.db
/volume1/screenpipe/#recycle/Copy #3 of db.sqlite
/volume1/screenpipe/#recycle/Copy #4 of db.sqlite
/volume1/screenpipe/#recycle/Copy #6 of archive.db
/volume1/screenpipe/#recycle/test.txt
/volume1/screenpipe/#recycle/Copy #7 of archive.db
/volume1/screenpipe/#recycle/Copy #8 of archive.db
/volume1/screenpipe/#recycle/archive.db-journal
/volume1/screenpipe/#recycle/Copy #1 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #2 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #3 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #4 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #6 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #7 of archive.db-journal
/volume1/screenpipe/#recycle/Copy #5 of db.sqlite
/volume1/screenpipe/pipes/.DS_Store
/volume1/screenpipe/app/.env
/volume1/screenpipe/app/cli.py
/volume1/screenpipe/app/.DS_Store
/volume1/screenpipe/app/db.py
/volume1/screenpipe/app/docker-compose.yml
/volume1/screenpipe/app/main.py
/volume1/screenpipe/app/requirements.txt
/volume1/screenpipe/app/Dockerfile
/volume1/screenpipe/data/.DS_Store
/volume1/screenpipe/.git/description
/volume1/screenpipe/.git/HEAD
/volume1/screenpipe/.git/index
/volume1/screenpipe/.git/COMMIT_EDITMSG
/volume1/screenpipe/#recycle/data/.DS_Store
---
app
app_settings.json
archive.db
data
db.sqlite
db.sqlite-shm
db.sqlite-wal
pipes
#recycle
screenpipe.db
screenpipe_sync.sh
Read
main.py
main.py
Bash
Check pipes directory and docker-compose
IN
ls /volume1/screenpipe/pipes/ && ls /volume1/screenpipe/app/ && cat /volume1/screenpipe/app/docker-compose.yml
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
cli.py
consumers
db.py
docker-compose.yml
Dockerfile
main.py
__pycache__
requirements.txt
static
services:
screenpipe-app:
build: .
container_name: screenpipe-app
restart: unless-stopped
ports:
- "8766:8000"
volumes:
- /volume1/screenpipe:/data
env_file:
- .env
environment:
TZ: Europe/Sofia
DB_PATH: /data/db.sqlite
sqlite-web-archive:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-archive
restart: unless-stopped
ports:
- "8767:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/archive.db"]
sqlite-web-live:
image: ghcr.io/coleifer/sqlite-web:latest
container_name: screenpipe-sqlweb-live
restart: unless-stopped
ports:
- "8768:8080"
volumes:
- /volume1/screenpipe:/data
command: ["-H", "[IP_ADDRESS]", "-r", "/data/db.sqlite"]
Read
requirements.txt
requirements.txt
Bash
Inspect a pipe directory
IN
ls /volume1/screenpipe/pipes/day-recap/ && cat /volume1/screenpipe/pipes/day-recap/pipe.json 2>/dev/null || ls /volume1/screenpipe/pipes/day-recap/
Copy code to clipboard
OUT
pipe.md
pipe.md
Read
cli.py
cli.py
Bash
List all pipes and their contents
IN
ls /volume1/screenpipe/pipes/ && for d in /volume1/screenpipe/pipes/*/; do echo "=== $d ==="; ls "$d"; done
Copy code to clipboard
OUT
ai-habits
day-recap
meeting-summary
standup-update
time-breakdown
video-export
=== /volume1/screenpipe/pipes/ai-habits/ ===
pipe.md
=== /volume1/screenpipe/pipes/day-recap/ ===
pipe.md
=== /volume1/screenpipe/pipes/meeting-summary/ ===
pipe.md
=== /volume1/screenpipe/pipes/standup-update/ ===
pipe.md
=== /volume1/screenpipe/pipes/time-breakdown/ ===
pipe.md
=== /volume1/screenpipe/pipes/video-export/ ===
pipe.md
Bash
Read pipe markdown files
IN
cat /volume1/screenpipe/pipes/day-recap/pipe.md && echo "===" && cat /volume1/screenpipe/pipes/meeting-summary/pipe.md 2>/dev/null | head -50
Copy code to clipboard
OUT
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
Thinking
Thinking
Bash
Read summary consumer
IN
ls /volume1/screenpipe/app/consumers/ && cat /volume1/screenpipe/app/consumers/summary.py
Copy code to clipboard
OUT
activity.py
audio.py
elements.py
__init__.py
interactions.py
ocr.py
__pycache__
report.py
summary.py
"""AI summary generator using Claude."""
import os
from datetime import date
from typing import Any
from consumers.activity import app_time, summary_stats, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
SUMMARY_TYPES = {
"day_recap": {
"title": "Day Recap",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a concise day recap using EXACTLY this format:
## Summary
One sentence: what I mainly worked on today.
## Accomplishments
- Top 3 things I finished, with approximate times
- Name specific apps, files, or projects
## Key Moments
- Important things seen or heard, with timestamps
## Unfinished Work
- What to continue tomorrow
## Patterns
- Apps used most, topics that came up repeatedly
Only report what you can verify from the data. End with:
**Next step:** [most important thing to continue]""",
},
"standup": {
"title": "Standup Update",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
## Audio/speech:
{audio}
Write a brief standup update:
**Yesterday:** What I worked on (2-3 bullets)
**Today:** What I plan to continue (1-2 bullets)
**Blockers:** Any issues observed (or "None")
Keep it under 150 words. Only report what's verifiable from the data.""",
},
"focus_time": {
"title": "Focus & Distraction Analysis",
"prompt": """\
You are analyzing a person's computer activity for the day.
## App usage (minutes per app):
{app_time}
## Browser URLs visited:
{browser_urls}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_events}
## Screen content (sampled every 5 minutes):
{ocr_text}
Analyze focus vs distraction patterns:
## Deep Work Periods
- When and how long were sustained focus sessions?
- What was being worked on?
## Distractions
- Which apps/sites were used recreationally?
- How much time was lost to context switching?
## Recommendations
- 2-3 concrete suggestions to improve focus tomorrow
Be specific with times and app names.""",
},
}
def _build_context(for_date: date) -> dict[str, str]:
apps = app_time(for_date)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(for_date, limit=20)
url_lines = "\n".join(
f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls
)
ui_rows = ui_event_summary(for_date)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(for_date, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(for_date)
return {
"app_time": app_lines or "(no app data)",
"browser_urls": url_lines or "(no browser data)",
"ui_events": ui_lines or "(no UI event data)",
"ocr_text": ocr_lines or "(no screen data)",
"audio": audio[:3000] if len(audio) > 3000 else audio,
}
def generate(
summary_type: str = "day_recap",
for_date: date | None = None,
api_key: str | None = None,
) -> dict[str, Any]:
"""Generate an AI summary. Returns dict with 'title', 'content', 'date'."""
import anthropic
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {
"title": "Error",
"content": "ANTHROPIC_API_KEY not set. Add it to your .env file.",
"date": str(d),
}
spec = SUMMARY_TYPES.get(summary_type)
if not spec:
return {"title": "Error", "content": f"Unknown summary type: {summary_type}", "date": str(d)}
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {
"title": spec["title"],
"content": f"No screen data found for {d}.",
"date": str(d),
}
ctx = _build_context(d)
prompt = spec["prompt"].format(**ctx)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
messages=[{"role": "user", "content": prompt}],
)
return {
"title": spec["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Thinking
Thinking
Bash
Read all pipe.md files
IN
for f in /volume1/screenpipe/pipes/*/pipe.md; do echo "=== $f ==="; cat "$f"; echo; done
Copy code to clipboard
OUT
=== /volume1/screenpipe/pipes/ai-habits/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: AI Habits
description: "How you use AI tools — patterns and insights"
icon: "🤖"
featured: true
---
Search my recordings from the last 24 hours for AI tool usage. Use app_name filter for each tool separately: ChatGPT, Claude, Copilot, Cursor, Gemini, Perplexity. Use limit=5 per search, max 6 searches total.
Read screenpipe skill first.
Use this exact format:
## AI Tools Used
- List each tool with approximate time spent (e.g. "Claude: ~45min")
## What I Used Them For
- For each tool: coding, writing, research, or brainstorming
## Usage Patterns
- Do I switch between tools? Use them in bursts or steadily?
## Effectiveness
- Which tool appeared alongside completed work vs. abandoned attempts
If no AI usage is found, say so clearly. End with: "**Tip:** [one suggestion to use AI tools more effectively]"
=== /volume1/screenpipe/pipes/day-recap/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Day Recap
description: "Today's accomplishments, key moments, and unfinished work"
icon: "📋"
featured: true
---
Analyze my screen and audio recordings from today (last 16 hours only).
Read screenpipe skill first.
Use this exact format:
## Summary
One sentence: what I mainly did today.
## Accomplishments
- Top 3 things I finished, with timestamps (e.g. "2:30 PM")
- Name specific apps, files, or projects
## Key Moments
- Important things I saw, said, or heard — with timestamps
## Unfinished Work
- What I should continue tomorrow — name the app/file/task
## Patterns
- Apps I used most, topics that came up repeatedly
Only report what you can verify from the data. End with: "**Next step:** [most important thing to continue]"
=== /volume1/screenpipe/pipes/meeting-summary/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Meeting Summary
description: "Summarize meeting transcript with key takeaways and action items"
icon: "🤝"
featured: false
---
Summarize the meeting transcript provided in the context. Include key takeaways and action items. If the meeting is marked as ongoing, note that and summarize what's available so far.
Read screenpipe skill first.
Use this exact format:
## Meeting Summary
One sentence: what this meeting was about.
## Key Takeaways
- Top 3-5 important points discussed
- Include who said what when relevant
## Action Items
- [ ] Task — assigned to whom, deadline if mentioned
- [ ] Task — assigned to whom
## Decisions Made
- List any decisions or agreements reached
## Open Questions
- Anything unresolved or needing follow-up
Keep it concise and actionable.
=== /volume1/screenpipe/pipes/standup-update/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Standup Update
description: "What you did, what's next, and any blockers"
icon: "🏢"
featured: true
---
Based on my recordings from the last 24 hours, generate a standup update. Use limit=10 per search, max 3 searches total.
Read screenpipe skill first.
Use this exact format:
## Yesterday
- What I worked on (name specific projects, files, tools, PRs)
## Today
- What I will work on next (based on unfinished tasks and recent activity)
## Blockers
- Issues I hit — errors, slow builds, waiting on someone
- If no blockers, write "None"
Keep it under 150 words. Copy-paste ready for a team standup.
=== /volume1/screenpipe/pipes/time-breakdown/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Time Breakdown
description: "Where your time went — by app, project, and category"
icon: "⏱"
featured: false
---
Analyze my app usage from today (last 12 hours). Use limit=10 per search, max 4 searches. Prefer /raw_sql with COUNT/GROUP BY queries.
Read screenpipe skill first.
Use this exact format with durations and percentages:
## By Application
- List each app with duration and percentage, sorted by time (e.g. "VS Code: 2h 15min (28%)")
## By Category
- Group into: coding, meetings, browsing, writing, communication, other
- Show hours and percentage per category
## By Project
- Group related activities by project/topic. Name specific repos or tasks.
## Productivity Score
- Calculate: focused_work_hours / total_hours as a percentage
- Focused = coding + writing. Unfocused = browsing + switching.
End with: "**Suggestion:** [one specific change to improve tomorrow's productivity]"
=== /volume1/screenpipe/pipes/video-export/pipe.md ===
---
schedule: manual
enabled: true
template: true
title: Export Video Clip
description: "Create a video of your recent screen activity"
icon: "🎬"
featured: false
---
Export a video of my screen activity from the last 5 minutes.
Read screenpipe skill first.
Use the POST /frames/export endpoint with the time range and fps=1.0. Then show me the exported video file path as an inline code block so I can watch it.
If the export is large, suggest a lower fps or shorter time range.
Thinking
Thinking
Now I have a clear picture. The pipes are markdown prompt templates in
/volume1/screenpipe/pipes/
, but there's no code to actually load and run them —
consumers/summary.py
has its own hardcoded prompts instead.
Here's what I'll implement:
consumers/pipes.py
— dynamically loads pipe.md files and runs them via Claude (data injected as system message, pipe body as user prompt)
main.py
— two new endpoints:
GET /api/pipes
and
POST /api/pipes/{pipe_id}/run
cli.py
— a
pipe
command to run pipes from the terminal
Let me build it:
Bash
Check browser_urls signature
IN
cat /volume1/screenpipe/app/consumers/activity.py | grep "def browser_urls" -A 5
Copy code to clipboard
OUT
def browser_urls(
for_date: date | None = None,
app_name: str | None = None,
ts_from: str | None = None,
ts_to: str | None = None,
limit: int = 30,
Write
pipes.py
pipes.py
143 lines
"""Dynamic pipe loader and runner."""
import os
import re
from datetime import date
from pathlib import Path
from typing import Any
def _parse_frontmatter(text: str) -> tuple[dict, str]:
if not text.startswith("---"):
return {}, text
try:
end = text.index("---", 3)
except ValueError:
return {}, text
fm_text = text[3:end].strip()
body = text[end + 3:].strip()
meta: dict = {}
for line in fm_text.splitlines():
if ":" in line:
k, _, v = line.partition(":")
meta[k.strip()] = v.strip().strip('"')
return meta, body
def load_pipes(pipes_dir: Path) -> list[dict]:
if not pipes_dir.exists():
return []
pipes = []
for pipe_dir in sorted(pipes_dir.iterdir()):
if not pipe_dir.is_dir() or pipe_dir.name.startswith("."):
continue
pipe_md = pipe_dir / "pipe.md"
if not pipe_md.exists():
continue
text = pipe_md.read_text(encoding="utf-8")
meta, body = _parse_frontmatter(text)
if meta.get("enabled", "true").lower() == "false":
continue
body = re.sub(r"Read screenpipe skill first\.?\n?", "", body).strip()
pipes.append({
"id": pipe_dir.name,
"title": meta.get("title", pipe_dir.name),
"description": meta.get("description", ""),
"icon": meta.get("icon", ""),
"schedule": meta.get("schedule", "manual"),
"featured": meta.get("featured", "false").lower() == "true",
"prompt": body,
})
return pipes
def _build_system(d: date, stats: dict) -> str:
from consumers.activity import app_time, browser_urls, ui_event_summary
from consumers.ocr import deduplicated_text
from consumers.audio import formatted_transcript
apps = app_time(d)
app_lines = "\n".join(f"- {a['app_name']}: {a['minutes']} min" for a in apps[:20])
urls = browser_urls(d, limit=20)
url_lines = "\n".join(f"- {u['browser_url'][:100]} ({u['minutes']} min)" for u in urls)
ui_rows = ui_event_summary(d)
ui_lines = "\n".join(
f"- {r['app_name']}: {r['clicks']} clicks, {r['keystrokes']} keys, {r['switches']} switches"
for r in ui_rows[:15]
)
ocr_rows = deduplicated_text(d, chunk_minutes=5)
ocr_lines = "\n".join(
f"[{r['bucket']}] {r['app_name']} / {r['window_name'] or ''}: {r['text'][:200]}"
for r in ocr_rows[:100]
)
audio = formatted_transcript(d)
if len(audio) > 3000:
audio = audio[:3000]
return f"""You are analyzing screenpipe data — recordings of a person's computer activity.
## App usage (minutes per app):
{app_lines or '(no app data)'}
## Browser URLs visited:
{url_lines or '(no browser data)'}
## UI activity per app (clicks / keystrokes / app-switches):
{ui_lines or '(no UI event data)'}
## Screen content (sampled every 5 minutes):
{ocr_lines or '(no screen data)'}
## Audio / speech:
{audio or '(no audio data)'}
Date: {d}
Total frames recorded: {stats['total_frames']}"""
def run_pipe(
pipe_id: str,
for_date: date | None = None,
api_key: str | None = None,
pipes_dir: Path | None = None,
) -> dict[str, Any]:
import anthropic
from consumers.activity import summary_stats
d = for_date or date.today()
key = api_key or os.environ.get("ANTHROPIC_API_KEY", "")
if not key:
return {"title": "Error", "content": "ANTHROPIC_API_KEY not set.", "date": str(d)}
_pipes_dir = pipes_dir or Path(os.environ.get("PIPES_DIR", "/data/pipes"))
all_pipes = {p["id"]: p for p in load_pipes(_pipes_dir)}
if pipe_id not in all_pipes:
return {"title": "Error", "content": f"Pipe not found: {pipe_id}", "date": str(d)}
pipe = all_pipes[pipe_id]
stats = summary_stats(d)
if stats["total_frames"] == 0:
return {"title": pipe["title"], "content": f"No screen data found for {d}.", "date": str(d)}
system = _build_system(d, stats)
client = anthropic.Anthropic(api_key=key)
message = client.messages.create(
model="claude-haiku-4-5-20251001",
max_tokens=1024,
system=system,
messages=[{"role": "user", "content": pipe["prompt"]}],
)
return {
"title": pipe["title"],
"content": message.content[0].text,
"date": str(d),
"stats": stats,
}
Now add the API endpoints to
main.py
:...
|
Code
|
screenpipe_sync.sh — screenpipe [SSH: nas]
|
NULL
|
21406
|