# screenpipe docs

## Docs

- [give AI memory of your screen](https://docs.screenpi.pe/ai-memory.md): Give Claude, Cursor, Ollama, and other LLMs persistent memory of everything on your screen so they can answer questions with full context.
- [Get activity summary](https://docs.screenpi.pe/api-reference/activity/get-activity-summary.md): Lightweight compressed activity overview for a time range. Returns app usage, recent accessibility texts, and audio summary (~200-500 tokens).
- [List audio devices](https://docs.screenpi.pe/api-reference/audio/list-audio-devices.md): Returns all available audio input and output devices.
- [Start audio recording](https://docs.screenpi.pe/api-reference/audio/start-audio-recording.md)
- [Start recording a specific audio device](https://docs.screenpi.pe/api-reference/audio/start-recording-a-specific-audio-device.md)
- [Stop audio recording](https://docs.screenpi.pe/api-reference/audio/stop-audio-recording.md)
- [Stop recording a specific audio device](https://docs.screenpi.pe/api-reference/audio/stop-recording-a-specific-audio-device.md)
- [Configure archive settings](https://docs.screenpi.pe/api-reference/cloud-archive/configure-archive-settings.md): POST /archive/configure — update retention or disable.
- [Get archive status](https://docs.screenpi.pe/api-reference/cloud-archive/get-archive-status.md): GET /archive/status — return current state.
- [Initialize cloud archive](https://docs.screenpi.pe/api-reference/cloud-archive/initialize-cloud-archive.md): POST /archive/init — initialize the archive system.
- [Run archive now](https://docs.screenpi.pe/api-reference/cloud-archive/run-archive-now.md): POST /archive/run — trigger an immediate archive run.
- [Download synced data](https://docs.screenpi.pe/api-reference/cloud-sync/download-synced-data.md): Download and import data from other devices.
- [Get sync status](https://docs.screenpi.pe/api-reference/cloud-sync/get-sync-status.md): Get current sync status.
- [Initialize cloud sync](https://docs.screenpi.pe/api-reference/cloud-sync/initialize-cloud-sync.md): Initialize sync at runtime with credentials.
- [Lock sync](https://docs.screenpi.pe/api-reference/cloud-sync/lock-sync.md): Lock sync (stop service and clear state).
- [Pull pipe configs from cloud](https://docs.screenpi.pe/api-reference/cloud-sync/pull-pipe-configs-from-cloud.md): Pull pipe manifest from cloud, merge with local, apply to disk.
- [Push pipe configs to cloud](https://docs.screenpi.pe/api-reference/cloud-sync/push-pipe-configs-to-cloud.md): Push local pipe manifest to cloud (merge with remote first).
- [Trigger sync](https://docs.screenpi.pe/api-reference/cloud-sync/trigger-sync.md): Trigger an immediate sync.
- [Delete data in time range](https://docs.screenpi.pe/api-reference/data-management/delete-data-in-time-range.md): Permanently delete all captured data (frames, OCR, audio, etc.) within a time range.
- [Delete device data](https://docs.screenpi.pe/api-reference/data-management/delete-device-data.md): Delete all locally-stored data that was synced from a specific remote device.
- [Get device storage usage](https://docs.screenpi.pe/api-reference/data-management/get-device-storage-usage.md): Get record counts per synced device.
- [Configure retention policy](https://docs.screenpi.pe/api-reference/data-retention/configure-retention-policy.md): POST /retention/configure — enable/disable local retention, set days.
- [Get retention status](https://docs.screenpi.pe/api-reference/data-retention/get-retention-status.md): GET /retention/status — return current retention state.
- [Run retention cleanup now](https://docs.screenpi.pe/api-reference/data-retention/run-retention-cleanup-now.md): POST /retention/run — trigger an immediate cleanup run.
- [Add content to database](https://docs.screenpi.pe/api-reference/database/add-content-to-database.md): Manually insert screen or audio content into the database.
- [Execute raw SQL](https://docs.screenpi.pe/api-reference/database/execute-raw-sql.md): Execute a raw SQL query against the screenpipe database. Use with caution.
- [Search UI elements](https://docs.screenpi.pe/api-reference/elements/search-ui-elements.md): Search elements across all frames with optional FTS, time, and app filters.
- [Merge video frames](https://docs.screenpi.pe/api-reference/experimental/merge-video-frames.md)
- [Validate media files](https://docs.screenpi.pe/api-reference/experimental/validate-media-files.md)
- [Get frame by ID](https://docs.screenpi.pe/api-reference/frames/get-frame-by-id.md): Returns a captured screenshot frame with optional base64 image data.
- [Get frame context](https://docs.screenpi.pe/api-reference/frames/get-frame-context.md): Get frame context: accessibility text, tree nodes, and extracted URLs. Falls back to OCR data for legacy frames without accessibility data.
- [Get frame metadata](https://docs.screenpi.pe/api-reference/frames/get-frame-metadata.md): Get frame metadata (timestamp) for deep link navigation. screenpipe://frame/123 → resolve to timestamp.
- [Get frame OCR (deprecated)](https://docs.screenpi.pe/api-reference/frames/get-frame-ocr-deprecated.md): Get OCR text positions with bounding boxes for a specific frame. Falls back to accessibility tree node bounds when no OCR data exists. Both OCR and accessibility bounds are normalized to 0-1 relative to the monitor (full-screen capture), so they align correctly with the screenshot.
- [Get frame text (OCR)](https://docs.screenpi.pe/api-reference/frames/get-frame-text-ocr.md): Get OCR text positions with bounding boxes for a specific frame. Falls back to accessibility tree node bounds when no OCR data exists. Both OCR and accessibility bounds are normalized to 0-1 relative to the monitor (full-screen capture), so they align correctly with the screenshot.
- [Get frame UI elements](https://docs.screenpi.pe/api-reference/frames/get-frame-ui-elements.md): Get all elements for a specific frame (full element tree).
- [Get next valid frame](https://docs.screenpi.pe/api-reference/frames/get-next-valid-frame.md): Find the next frame that has a valid video file on disk. This allows the frontend to skip directly to a valid frame instead of trying each frame one-by-one when frames fail to load.
- [Run frame OCR (deprecated)](https://docs.screenpi.pe/api-reference/frames/run-frame-ocr-deprecated.md): Run on-demand OCR on a frame that has no stored bounding boxes. Loads the snapshot JPEG, runs Apple Vision OCR, stores the result, and returns the text positions. Subsequent GET requests will hit the cached DB row. If OCR data already exists, returns it without re-running.
- [Run OCR on frame](https://docs.screenpi.pe/api-reference/frames/run-ocr-on-frame.md): Run on-demand OCR on a frame that has no stored bounding boxes. Loads the snapshot JPEG, runs Apple Vision OCR, stores the result, and returns the text positions. Subsequent GET requests will hit the cached DB row. If OCR data already exists, returns it without re-running.
- [Bulk delete meetings](https://docs.screenpi.pe/api-reference/meetings/bulk-delete-meetings.md)
- [Delete meeting](https://docs.screenpi.pe/api-reference/meetings/delete-meeting.md)
- [Get meeting by ID](https://docs.screenpi.pe/api-reference/meetings/get-meeting-by-id.md)
- [Get meeting detection status](https://docs.screenpi.pe/api-reference/meetings/get-meeting-detection-status.md)
- [List meetings](https://docs.screenpi.pe/api-reference/meetings/list-meetings.md): Returns detected and manually started meetings with transcriptions.
- [Merge meetings](https://docs.screenpi.pe/api-reference/meetings/merge-meetings.md)
- [Start a manual meeting](https://docs.screenpi.pe/api-reference/meetings/start-a-manual-meeting.md)
- [Stop a manual meeting](https://docs.screenpi.pe/api-reference/meetings/stop-a-manual-meeting.md)
- [Update meeting](https://docs.screenpi.pe/api-reference/meetings/update-meeting.md)
- [Create memory](https://docs.screenpi.pe/api-reference/memories/create-memory.md)
- [Delete memory](https://docs.screenpi.pe/api-reference/memories/delete-memory.md)
- [Get memory by ID](https://docs.screenpi.pe/api-reference/memories/get-memory-by-id.md)
- [List memories](https://docs.screenpi.pe/api-reference/memories/list-memories.md): Returns saved AI memories / knowledge extracted from screen activity.
- [Update memory](https://docs.screenpi.pe/api-reference/memories/update-memory.md)
- [Keyword search](https://docs.screenpi.pe/api-reference/search/keyword-search.md): Fast keyword-based search across all content types.
- [Search screen and audio content](https://docs.screenpi.pe/api-reference/search/search-screen-and-audio-content.md): Query captured screen text (OCR), audio transcriptions, and UI elements with filters for time range, app, window, content type, and more.
- [Delete speaker](https://docs.screenpi.pe/api-reference/speakers/delete-speaker.md)
- [Find similar speakers](https://docs.screenpi.pe/api-reference/speakers/find-similar-speakers.md)
- [List unnamed speakers](https://docs.screenpi.pe/api-reference/speakers/list-unnamed-speakers.md): Returns speakers that haven't been identified/named yet.
- [Mark speaker as hallucination](https://docs.screenpi.pe/api-reference/speakers/mark-speaker-as-hallucination.md): Flag a detected speaker as a false positive / hallucination.
- [Merge speakers](https://docs.screenpi.pe/api-reference/speakers/merge-speakers.md): Merge two speaker identities into one.
- [Reassign speaker](https://docs.screenpi.pe/api-reference/speakers/reassign-speaker.md): Reassign audio segments from one speaker to another.
- [Search speakers](https://docs.screenpi.pe/api-reference/speakers/search-speakers.md)
- [Undo speaker reassignment](https://docs.screenpi.pe/api-reference/speakers/undo-speaker-reassignment.md)
- [Update speaker name](https://docs.screenpi.pe/api-reference/speakers/update-speaker-name.md)
- [Health check](https://docs.screenpi.pe/api-reference/system/health-check.md): Returns system health status including audio/video pipeline state, device info, and version.
- [Add tags](https://docs.screenpi.pe/api-reference/tags/add-tags.md): Add tags to a specific content item (frame or audio chunk).
- [Get tags in batch](https://docs.screenpi.pe/api-reference/tags/get-tags-in-batch.md): Batch fetch tags for multiple vision frame IDs. POST /tags/vision/batch  { "frame_ids": [1, 2, 3] }
- [Remove tags](https://docs.screenpi.pe/api-reference/tags/remove-tags.md): Remove tags from a specific content item.
- [Get vault status](https://docs.screenpi.pe/api-reference/vault/get-vault-status.md): GET /vault/status
- [Lock vault](https://docs.screenpi.pe/api-reference/vault/lock-vault.md): POST /vault/lock
- [Set up vault](https://docs.screenpi.pe/api-reference/vault/set-up-vault.md): POST /vault/setup
- [Unlock vault](https://docs.screenpi.pe/api-reference/vault/unlock-vault.md): POST /vault/unlock
- [List monitors](https://docs.screenpi.pe/api-reference/vision/list-monitors.md): Returns all available monitors/displays.
- [Apple Intelligence: on-device summaries and reminders](https://docs.screenpi.pe/apple-intelligence.md): screenpipe uses Apple Intelligence (on-device Foundation Models) to generate daily summaries and automatically extract action items into Apple Reminders.
- [architecture](https://docs.screenpi.pe/architecture.md): How screenpipe uses event-driven capture, accessibility tree extraction, OCR fallback, and SQLite storage to build a searchable local memory of your screen.
- [changelog](https://docs.screenpi.pe/changelog.md): Track every screenpipe release: new features, performance improvements, bug fixes, and breaking changes across desktop and CLI versions.
- [ChatGPT — use your subscription with screenpipe](https://docs.screenpi.pe/chatgpt.md): Connect your ChatGPT Plus or Pro subscription to power screenpipe's AI chat and pipes with the latest OpenAI models — no API key required.
- [Claude Code - AI coding with screen context](https://docs.screenpi.pe/claude-code.md): Use screenpipe with Claude Code CLI to give Claude access to your screen history, meeting transcriptions, and app context while coding.
- [API reference](https://docs.screenpi.pe/cli-reference.md): Complete REST API reference for screenpipe at localhost:3030 — search screen history, query frames, audio transcripts, tags, health, and more endpoints.
- [cline - VS Code agent with screen memory](https://docs.screenpi.pe/cline.md): Connect screenpipe to Cline via MCP to give this autonomous VS Code coding agent access to your screen history, meetings, and app context.
- [cloud archive - free disk space automatically](https://docs.screenpi.pe/cloud-archive.md): Free disk space by encrypting old screenpipe screen recordings and uploading them to the cloud with zero-knowledge encryption — searchable on demand.
- [connect your apps](https://docs.screenpi.pe/connections.md): Connect 45+ apps to screenpipe — Slack, Notion, Gmail, Obsidian, Toggl, HubSpot, Salesforce, and more. Give your AI agents access to your full digital context.
- [continue - open-source copilot with screen context](https://docs.screenpi.pe/continue.md): Set up screenpipe with Continue, the open-source AI copilot for VS Code and JetBrains, so it can reference your screen history while you code.
- [contribute to screenpipe - open source screen recording](https://docs.screenpi.pe/contributing.md): Contribute to screenpipe: report bugs, submit pull requests, join bounty programs, and help build the open source screen recording platform.
- [FAQ](https://docs.screenpi.pe/faq.md): Common questions about screenpipe — what pipes are, how privacy works, supported platforms, AI models, storage, pricing, and how to get help.
- [screenpipe for developers](https://docs.screenpi.pe/for-developers.md): Give your AI coding assistant memory of your screen via MCP and the screenpipe REST API — works with Claude Code, Cursor, Cline, Continue, and Gemini CLI.
- [gemini CLI - google's AI with screen context](https://docs.screenpi.pe/gemini-cli.md): Connect screenpipe to Gemini CLI via MCP so Google's terminal AI assistant can reference your screen history and meeting transcriptions while you code.
- [install screenpipe](https://docs.screenpi.pe/getting-started.md): Install screenpipe on macOS, Windows, or Linux. Record everything on screen and search screen history on Mac, Windows, and Linux. Start recording in minutes.
- [screenpipe: open source 24/7 screen and audio memory for AI](https://docs.screenpi.pe/home.md): screenpipe captures your screen 24/7, extracts text with OCR, transcribes audio locally, and feeds it to AI assistants. Open source and privacy-focused.
- [MCP apps - create interactive UIs for screenpipe](https://docs.screenpi.pe/mcp-apps.md): Build interactive UI components — dashboards, forms, visualizations — that render directly inside Claude, ChatGPT, and VS Code using the MCP Apps protocol.
- [MCP server setup for Claude, Cursor, and other AI tools](https://docs.screenpi.pe/mcp-server.md): Set up screenpipe as a Model Context Protocol server so Claude Desktop, Cursor, and other AI assistants can search your screen history and audio transcripts.
- [meeting transcription](https://docs.screenpi.pe/meeting-transcription.md): Automatically transcribe Zoom, Meet, and Teams meetings locally with screenpipe using Whisper speech-to-text and speaker diarization — no bot, no cloud.
- [msty - privacy-first AI with screen context](https://docs.screenpi.pe/msty.md): Connect screenpipe to Msty's Toolbox via MCP (STDIO or HTTP) so this privacy-first desktop AI can search your screen history and meeting transcripts.
- [obsidian - sync screen history to your notes](https://docs.screenpi.pe/obsidian.md): Sync screenpipe's screen history and meeting transcripts into Obsidian via the Copilot plugin so you can query your activity from your local notes vault.
- [Ollama — run AI locally with screenpipe](https://docs.screenpi.pe/ollama.md): Run open-source LLMs like Llama, Qwen, and Mistral locally with Ollama and screenpipe — completely free, private, and offline with no API keys required.
- [OpenClaw - AI assistant with screenpipe memory](https://docs.screenpi.pe/openclaw.md): Connect screenpipe to OpenClaw, a self-hosted personal AI that ties into WhatsApp, Telegram, Discord, and iMessage, so it can recall your screen history.
- [OpenCode - terminal AI with screen memory](https://docs.screenpi.pe/opencode.md): Integrate screenpipe with OpenCode to give your terminal AI assistant access to your screen history, audio transcriptions, and app context.
- [pipe permissions](https://docs.screenpi.pe/pipe-permissions.md): Control which screenpipe API endpoints your pipes can access by allowlisting endpoints, restricting writes, and scoping permissions per automation.
- [pipe store — browse all automations](https://docs.screenpi.pe/pipe-store.md): Browse every screenpipe pipe: digital clone, meeting intelligence, time tracking, Obsidian sync, CRM, and more. One-click install from the app.
- [pipes — build your own automations](https://docs.screenpi.pe/pipes.md): Build custom AI automations that run on your screen data. Pipes are scheduled AI agents written in plain markdown — prompt plus schedule, no code required.
- [privacy filter - strip personal info before AI sees it](https://docs.screenpi.pe/privacy-filter.md): Strip names, emails, phone numbers, addresses, and account numbers from your screen data before AI sees it — inside a verifiable confidential-compute enclave.
- [5-minute quickstart](https://docs.screenpi.pe/quickstart.md): Go from install to your first AI-powered insight in under 5 minutes — set up screenpipe, connect your AI assistant, and run your first automation pipe.
- [search your screen history](https://docs.screenpi.pe/search-screen-history.md): Find any text, conversation, or activity from your screen history with screenpipe's local AI-powered search on Mac, Windows, and Linux.
- [teams — share configs with end-to-end encryption](https://docs.screenpi.pe/teams.md): Push pipe configurations and content filters to your team. Everything is encrypted client-side — the server only sees encrypted blobs.
- [troubleshooting](https://docs.screenpi.pe/troubleshooting.md): Fix common screenpipe issues including installation errors, screen and microphone permissions, missing audio, pipe failures, and MCP connection problems.
- [what can you do with screenpipe?](https://docs.screenpi.pe/use-cases.md): Everything you can do with screenpipe — from daily summaries to time tracking to meeting transcription. Organized by what you're trying to accomplish.
- [screenpipe vs Fathom: 24/7 screen memory vs meeting bot](https://docs.screenpi.pe/vs-fathom.md): Compare screenpipe and Fathom: 24/7 local screen plus audio capture vs cloud meeting transcription for Zoom, Meet, and Teams — features, pricing, and privacy.
- [screenpipe vs Fireflies.ai: local memory vs meeting bot](https://docs.screenpi.pe/vs-fireflies.md): Compare screenpipe and Fireflies.ai: local 24/7 screen and audio capture vs a cloud meeting bot with per-seat pricing and AI credit caps.
- [screenpipe vs Granola - full screen memory vs meeting notes](https://docs.screenpi.pe/vs-granola.md): Compare screenpipe and Granola: local 24/7 screen plus audio capture vs a cloud AI meeting notepad — features, pricing, and Google Workspace requirements.
- [screenpipe vs Limitless - self-hosted alternative](https://docs.screenpi.pe/vs-limitless.md): Compare screenpipe and Limitless.ai: a self-hosted, open source desktop screen recorder vs the Limitless AI pendant. Data ownership and privacy compared.
- [screenpipe vs Littlebird: local-first vs cloud screen AI](https://docs.screenpi.pe/vs-littlebird.md): Compare screenpipe and Littlebird: 100% local open-source screen plus audio capture vs a cloud-hosted screen reader. Privacy, data ownership, and features.
- [screenpipe vs Omi — desktop capture vs AI wearable](https://docs.screenpi.pe/vs-omi.md): Compare screenpipe and Omi (formerly Friend): desktop screen and audio capture vs an $89 AI wearable pendant. Two open-source approaches to AI memory.
- [screenpipe vs Otter.ai: local screen memory vs meeting bot](https://docs.screenpi.pe/vs-otter.md): Compare screenpipe and Otter.ai: local 24/7 screen and audio capture vs cloud meeting transcription with a 6000 minute monthly cap and a visible bot.
- [screenpipe vs Pieces for Developers](https://docs.screenpi.pe/vs-pieces.md): Compare screenpipe to Pieces for Developers. Full screen capture vs code snippet manager. screenpipe captures everything — Pieces only sees your editor.
- [screenpipe vs Microsoft Recall - privacy-focused alternative](https://docs.screenpi.pe/vs-recall.md): Compare screenpipe and Microsoft Recall: an open-source Windows Recall alternative that runs on Mac, Windows, and Linux with no cloud dependency.
- [screenpipe vs Rewind.ai - open source alternative](https://docs.screenpi.pe/vs-rewind.md): Compare screenpipe and Rewind.ai: an open-source, local-first, cross-platform Rewind alternative now that Rewind has pivoted to Limitless.

## OpenAPI Specs

- [openapi](https://docs.screenpi.pe/openapi.yaml)