# Screenpipe docs

- [Screenpipe: local-first 24/7 screen and audio memory for AI](https://docs.screenpipe.com/home.md): Screenpipe captures your screen 24/7, reads app text through accessibility APIs, transcribes audio locally, and feeds it to AI assistants.
- [Screenpipe quickstart: install and connect AI in 5 minutes](https://docs.screenpipe.com/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 scheduled task.
- [Get your first useful result](https://docs.screenpipe.com/first-useful-result.md): Choose one real task, check its recording, and produce a useful report with a copyable prompt and a clear success check.
- [Recording, memory, workflows, and automation: what is the difference?](https://docs.screenpipe.com/recording-memory-and-automation.md): Screenpipe captures available screen and audio context while recording is running.
- [Install Screenpipe on macOS, Windows, and Linux](https://docs.screenpipe.com/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.
- [What can you do with Screenpipe?](https://docs.screenpipe.com/use-cases.md): Practical, step-by-step workflows for time tracking, remote-support job logs, client reporting, research, meetings, follow-up, SOPs, and local AI memory.
- [Screenpipe architecture: event-driven capture and storage](https://docs.screenpipe.com/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.
- [Choose what Screenpipe records](https://docs.screenpipe.com/recording-controls.md): Use recording and privacy controls to limit the context you capture, then test the result with harmless sample content.
- [Find out why screen history or transcripts are missing](https://docs.screenpipe.com/missing-recordings.md): A missing answer can come from capture, transcription, search scope, sync, or report generation.
- [Plan Screenpipe storage and retention](https://docs.screenpipe.com/storage-and-retention.md): Storage use depends on what you capture and retain.
- [Choose local or cloud AI for recorded work](https://docs.screenpipe.com/local-or-cloud-ai.md): Choose the AI provider separately from your recording and storage settings.
- [Give your assistant access to Screenpipe history](https://docs.screenpipe.com/connect-your-assistant.md): An assistant needs an actual connection to retrieve Screenpipe history.
- [Task library — browse all automations](https://docs.screenpipe.com/task-library.md): Browse every Screenpipe scheduled task: digital clone, meeting intelligence, time tracking, Obsidian sync, CRM, and more. One-click install from the app.
- [Build and manage scheduled tasks](https://docs.screenpipe.com/scheduled-tasks.md): Build custom AI automations that run on your screen data. Scheduled tasks are scheduled AI agents written in plain markdown — prompt plus schedule, no code required.
- [Build a scheduled report you can verify](https://docs.screenpipe.com/reliable-reports.md): Create a recurring report with an explicit source window, saved output, run receipt, no-data state, and a repeatable verification process.
- [Understand AI usage and control scheduled work](https://docs.screenpipe.com/ai-usage-and-controls.md): Understand hosted allowance, provider usage, background tasks, warnings, and the difference between stopping a run and disabling its schedule.
- [Troubleshoot scheduled tasks](https://docs.screenpipe.com/task-troubleshooting.md): A practical debugging guide for Screenpipe scheduled tasks: schedules, logs, API access, AI provider auth, connection proxies, permissions, and stuck runs.
- [Scheduled task permissions: scope Screenpipe API access](https://docs.screenpipe.com/task-permissions.md): Control which Screenpipe API endpoints your scheduled tasks can access by allowlisting endpoints, restricting writes, and scoping permissions per automation.
- [MCP server setup for Codex, Claude, Cursor, and AI tools](https://docs.screenpipe.com/mcp-server.md): Set up Screenpipe as a Model Context Protocol server so Codex, Claude, and Cursor can search your screen history and audio transcripts.
- [Connect Slack, Notion, Calendar, and other apps](https://docs.screenpipe.com/connections.md): Connect Slack, Notion, Google Calendar, Obsidian, HubSpot, Salesforce, Zoom, PostHog, and Sentry to Screenpipe so AI agents get structured app context.
- [Connection reference: auth, proxies, and credentials](https://docs.screenpipe.com/connection-reference.md): Reference for Screenpipe app connections: available integrations, auth style, proxy usage, multi-account support, credential storage, and test queries.
- [Privacy data flow: what Screenpipe captures and stores](https://docs.screenpipe.com/privacy-data-flow.md): What Screenpipe captures, where it is stored locally, when data can leave your machine, and the controls that keep screen and audio data private.
- [Privacy filter - strip personal info before AI sees it](https://docs.screenpipe.com/privacy-filter.md): Strip names, emails, phone numbers, addresses, and secrets from Screenpipe data before AI sees it, using local redaction or a confidential enclave.
- [Teams — share configs with end-to-end encryption](https://docs.screenpipe.com/teams.md): Push scheduled task configurations and content filters to your team. Everything is encrypted client-side — the server only sees encrypted blobs.
- [Consultant time tracking](https://docs.screenpipe.com/consultant-time-tracking.md): Track consultant hours across calls, docs, code, and browsers with Screenpipe. Produce a reviewed client time report without invasive monitoring.
- [Remote-support job logs and billing reports](https://docs.screenpipe.com/remote-support-job-reports.md): Ten copyable prompts for IT support: reconstruct jobs, review client time, connect email context, export service reports, and control scheduled AI work.
- [Weekly client reports from real work](https://docs.screenpipe.com/client-weekly-report.md): Build a client-ready weekly consulting report with active time, deliverables, decisions, risks, and next steps from a bounded Screenpipe work history.
- [Discover work worth automating](https://docs.screenpipe.com/workflow-discovery.md): Observe a few real Screenpipe recordings to find one repeated workflow, measure its friction and handoffs, and turn activity into an automation candidate.
- [Turn a work session into a detailed workflow handoff](https://docs.screenpipe.com/workflow-handoff.md): Build a source-backed SOP and automation handoff with concrete inputs, decision rules, screenshots when available, exceptions, and acceptance checks.
- [Daily work review](https://docs.screenpipe.com/daily-work-review.md): Turn a day of screen and meeting activity into a private recap, standup draft, or open-loops list using Screenpipe timeline search and Home scheduled tasks.
- [Build a daily project brief in your existing notes](https://docs.screenpipe.com/daily-project-brief.md): Use recorded work to maintain a small Markdown or Obsidian brief with decisions, open loops, source references, and explicit coverage gaps.
- [Turn browser research into a checked brief](https://docs.screenpipe.com/research-brief.md): Recover pages, documents, and questions from a bounded research session, then create a concise brief that preserves sources and uncertainty.
- [Relationship context and follow-up](https://docs.screenpipe.com/relationship-follow-up.md): Create a private, reviewed follow-up queue from meetings and on-screen conversations without automatically messaging people or inventing commitments.
- [Meeting notes to follow-up](https://docs.screenpipe.com/meeting-follow-up.md): Capture a meeting with Screenpipe, verify the transcript, and produce decisions, owners, action items, and a reviewed follow-up email or CRM update draft.
- [Turn a verified meeting into a CRM update](https://docs.screenpipe.com/meeting-to-crm.md): Extract reviewed contact, deal, decision, objection, and next-step fields from a meeting without automatically writing uncertain data.
- [Reconstruct a support or engineering incident](https://docs.screenpipe.com/incident-reconstruction.md): Build a bounded incident timeline from screens, logs, calls, and messages while separating observed facts, inference, and unknowns.
- [Monitor one approved window or website](https://docs.screenpipe.com/focused-monitoring.md): Create a narrow local Screenpipe monitor for one approved app, window, or website with recording filters, explicit no-data states, and reviewed alerts.
- [Local memory for AI agents](https://docs.screenpipe.com/agent-memory-workflow.md): Give Claude, Codex, Cursor, and other AI agents continuity across sessions with small source-backed local context files built from Screenpipe history.
- [Capture a workflow as an SOP](https://docs.screenpipe.com/team-sop-capture.md): Record one clean run of a real workflow with Screenpipe, then draft a reviewed team SOP with prerequisites, decisions, exceptions, and evidence gaps.
- [Search your screen history](https://docs.screenpipe.com/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.
- [Meeting intelligence: botless transcripts and summaries](https://docs.screenpipe.com/meeting-intelligence.md): Use Screenpipe for botless meeting memory: live transcripts, speaker naming, calendar context, summaries, transcript copy, and API automation.
- [Local meeting transcription for Zoom, Meet, and Teams](https://docs.screenpipe.com/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.
- [Give AI memory of your screen](https://docs.screenpipe.com/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.
- [Build a second brain in your agent](https://docs.screenpipe.com/second-brain.md): Turn any agent — OpenClaw, Hermes, Claude, or Codex — into a second brain that watches your Screenpipe activity and remembers your workflows.
- [Screenpipe for developers: MCP and REST API for AI coding](https://docs.screenpipe.com/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.
- [Prepare for a meeting from previous conversations](https://docs.screenpipe.com/meeting-preparation.md): Build a short brief from the latest relevant conversations, then verify current calendar and communication state.
- [Compare your weekly plans with recorded work](https://docs.screenpipe.com/weekly-work-review.md): Use a weekly review to compare your intended outcomes with observable work and decide what to change.
- [Build an engineering decision log from recorded work](https://docs.screenpipe.com/engineering-decision-log.md): A useful engineering memory explains why a decision was made, the evidence behind it, and whether it still applies.
- [Share useful team knowledge from recorded work](https://docs.screenpipe.com/share-team-knowledge.md): Share a reviewed answer or process note with its intended audience, rather than assuming everyone should access the underlying workday.
- [Create a role handoff before a teammate leaves](https://docs.screenpipe.com/role-handoffs.md): A good role handoff captures recurring responsibilities, decision rules, exceptions, and where work stands.
- [Turn resolved support cases into useful help articles](https://docs.screenpipe.com/support-knowledge-base.md): Use resolved cases to explain a repeatable symptom, diagnosis, correction, and verification.
- [Document a spreadsheet reconciliation workflow](https://docs.screenpipe.com/spreadsheet-workflow-documentation.md): Screen history can show how a person moves through a reconciliation, but visible cells do not reveal every formula, hidden sheet, macro, or business rule.
- [Document a browser form or portal workflow](https://docs.screenpipe.com/browser-workflow-documentation.md): A browser workflow needs more than a list of pages.
- [Turn a customer meeting into engineering ticket drafts](https://docs.screenpipe.com/meeting-to-engineering-tickets.md): Turn a reported problem into a ticket that separates the customer’s observation from a verified reproduction.
- [Choose which observed workflow to automate first](https://docs.screenpipe.com/automation-prioritization.md): Prioritize a repeated, well-understood task with a clear success check.
- [Test an automation against real workflow requirements](https://docs.screenpipe.com/automation-validation.md): Validate the output and side effects against agreed requirements, not just a successful run status.
- [Plan a Screenpipe enterprise pilot with a measurable result](https://docs.screenpipe.com/enterprise-pilot.md): Start with one workflow, a small participating group, and one agreed output.
- [Check enterprise device capture and data coverage](https://docs.screenpipe.com/enterprise-device-coverage.md): Check local capture, uploaded data, and generated reports separately for each pilot device.
- [Prepare a security review for a Screenpipe workflow](https://docs.screenpipe.com/enterprise-security-review.md): Review the actual workflow’s data path and enabled controls.
- [ChatGPT — use your subscription with Screenpipe](https://docs.screenpipe.com/chatgpt.md): Connect your ChatGPT Plus or Pro subscription to power Screenpipe's AI chat and scheduled tasks with the latest OpenAI models — no API key required.
- [Ollama — run AI locally with Screenpipe](https://docs.screenpipe.com/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.
- [Claude Code - AI coding with screen context](https://docs.screenpipe.com/claude-code.md): Use Screenpipe with Claude Code CLI to give Claude access to your screen history, meeting transcriptions, and app context while coding.
- [OpenCode - terminal AI with screen memory](https://docs.screenpipe.com/opencode.md): Integrate Screenpipe with OpenCode to give your terminal AI assistant access to your screen history, audio transcriptions, and app context.
- [OpenClaw - AI assistant with Screenpipe memory](https://docs.screenpipe.com/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.
- [Hermes - Screenpipe context for your agent](https://docs.screenpipe.com/hermes.md): Connect Hermes to Screenpipe with MCP and skills to recall screen history and meetings.
- [Cline - VS Code agent with screen memory](https://docs.screenpipe.com/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.
- [Continue - open-source copilot with screen context](https://docs.screenpipe.com/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.
- [Gemini CLI - Google's AI with screen context](https://docs.screenpipe.com/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.
- [GitHub Copilot CLI — agentic coding with screen context](https://docs.screenpipe.com/copilot-cli.md): Connect Screenpipe to GitHub Copilot CLI via MCP so Copilot can reference your screen history, meeting transcriptions, and app context from the terminal.
- [Obsidian - sync screen history to your notes](https://docs.screenpipe.com/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.
- [Msty - privacy-first AI with screen context](https://docs.screenpipe.com/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.
- [Screenpipe API recipes](https://docs.screenpipe.com/api-recipes.md): Copy-paste recipes for the most useful Screenpipe API workflows: search, meetings, speakers, frames, memories, retention, and safe data deletion.
- [Screenpipe REST API reference at localhost:3030](https://docs.screenpipe.com/cli-reference.md): Complete REST API reference for Screenpipe at localhost:3030 — search screen history, query frames, audio transcripts, tags, health, and more endpoints.
- [Deploy Screenpipe via Microsoft Intune](https://docs.screenpipe.com/intune-deployment.md): Fleet-deploy Screenpipe enterprise to Windows devices via Microsoft Intune by assigning a Microsoft Entra group for automatic installation.
- [Screenpipe vs Pieces: screen capture vs code snippets](https://docs.screenpipe.com/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 Littlebird: local-first vs cloud screen AI](https://docs.screenpipe.com/vs-littlebird.md): Compare Screenpipe and Littlebird: 100% local source-available 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.screenpipe.com/vs-omi.md): Compare Screenpipe and Omi (formerly Friend): desktop screen and audio capture vs an $89 AI wearable pendant. Two auditable approaches to AI memory.
- [Screenpipe vs Granola - full screen memory vs meeting notes](https://docs.screenpipe.com/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 Rewind.ai - local-first alternative](https://docs.screenpipe.com/vs-rewind.md): Compare Screenpipe and Rewind.ai: a source-available, local-first, cross-platform Rewind alternative now that Rewind has pivoted to Limitless.
- [Screenpipe vs Microsoft Recall - privacy-focused alternative](https://docs.screenpipe.com/vs-recall.md): Compare Screenpipe and Microsoft Recall: a source-available Windows Recall alternative that runs on Mac, Windows, and Linux with no cloud dependency.
- [Screenpipe vs Limitless - self-hosted alternative](https://docs.screenpipe.com/vs-limitless.md): Compare Screenpipe and Limitless.ai: a self-hosted, source-available desktop screen recorder vs the Limitless AI pendant. Data ownership and privacy compared.
- [Screenpipe vs Otter.ai: local screen memory vs meeting bot](https://docs.screenpipe.com/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 Fathom: 24/7 screen memory vs meeting bot](https://docs.screenpipe.com/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.screenpipe.com/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.
- [Troubleshoot Screenpipe: install, permissions, and scheduled tasks](https://docs.screenpipe.com/troubleshooting.md): Fix common Screenpipe issues including installation errors, screen and microphone permissions, missing audio, scheduled task failures, and MCP connection problems.
- [Fix screen recording permission on macOS for Screenpipe](https://docs.screenpipe.com/permissions.md): Grant, reset, and recover macOS Screen Recording permission for Screenpipe — covers per-bundle-id TCC, tccutil commands, and System Settings steps.
- [Screenpipe FAQ: install, permissions, scheduled tasks, and privacy](https://docs.screenpipe.com/faq.md): Answers to common Screenpipe questions on install, screen and mic permissions, Zoom and Teams transcription, scheduled tasks, AI keys, Ollama, and privacy.
- [Contribute to Screenpipe - local-first screen recording](https://docs.screenpipe.com/contributing.md): Contribute to Screenpipe: report bugs, submit pull requests, join bounty programs, and help build the local-first screen recording platform.
- [Docs maintenance guide for Screenpipe contributors](https://docs.screenpipe.com/docs-maintenance.md): How Screenpipe maintainers keep docs synced with product changes, OpenAPI routes, app connections, UI screenshots, and changelog release notes.
- [Screenpipe changelog: releases, features, and fixes](https://docs.screenpipe.com/changelog.md): Track every Screenpipe release: new features, performance improvements, bug fixes, and breaking changes across desktop and CLI versions.
- [Search screen and audio content](https://docs.screenpipe.com/api-reference/search/search-screen-and-audio-content.md): Query captured screen text (accessibility-first with OCR fallback), audio transcriptions, and UI elements with filters for time range, app, window, content type, and more.
- [Keyword search](https://docs.screenpipe.com/api-reference/search/keyword-search.md): Fast keyword-based search across all content types.
- [List audio devices](https://docs.screenpipe.com/api-reference/audio/list-audio-devices.md): Returns all available audio input and output devices.
- [Start audio recording](https://docs.screenpipe.com/api-reference/audio/start-audio-recording.md)
- [Stop audio recording](https://docs.screenpipe.com/api-reference/audio/stop-audio-recording.md)
- [Start recording a specific audio device](https://docs.screenpipe.com/api-reference/audio/start-recording-a-specific-audio-device.md)
- [Stop recording a specific audio device](https://docs.screenpipe.com/api-reference/audio/stop-recording-a-specific-audio-device.md)
- [List monitors](https://docs.screenpipe.com/api-reference/vision/list-monitors.md): Returns all available monitors/displays.
- [Get tags in batch](https://docs.screenpipe.com/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] }
- [Add tags](https://docs.screenpipe.com/api-reference/tags/add-tags.md): Add tags to a specific content item (frame or audio chunk).
- [Remove tags](https://docs.screenpipe.com/api-reference/tags/remove-tags.md): Remove tags from a specific content item.
- [Get frame by ID](https://docs.screenpipe.com/api-reference/frames/get-frame-by-id.md): Returns a captured screenshot frame with optional base64 image data.
- [Get frame text and bounds](https://docs.screenpipe.com/api-reference/frames/get-frame-text-and-bounds.md): Get frame text positions with bounding boxes for a specific frame. Uses accessibility tree node bounds when available, and OCR fallback positions for visual-only or legacy frames. Both OCR and accessibility bounds are normalized to 0-1 relative to the monitor (full-screen capture), so they align cor…
- [Run OCR on frame](https://docs.screenpipe.com/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.
- [Get frame OCR (deprecated)](https://docs.screenpipe.com/api-reference/frames/get-frame-ocr-deprecated.md): Get frame text positions with bounding boxes for a specific frame. Uses accessibility tree node bounds when available, and OCR fallback positions for visual-only or legacy frames. Both OCR and accessibility bounds are normalized to 0-1 relative to the monitor (full-screen capture), so they align cor…
- [Run frame OCR (deprecated)](https://docs.screenpipe.com/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.
- [Get frame context](https://docs.screenpipe.com/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.screenpipe.com/api-reference/frames/get-frame-metadata.md): Get frame metadata (timestamp) for deep link navigation. screenpipe://frame/123 → resolve to timestamp.
- [Get next valid frame](https://docs.screenpipe.com/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.
- [Get frame UI elements](https://docs.screenpipe.com/api-reference/frames/get-frame-ui-elements.md): Get all elements for a specific frame (full element tree).
- [Health check](https://docs.screenpipe.com/api-reference/system/health-check.md): Returns system health status including audio/video pipeline state, device info, and version.
- [Execute raw SQL](https://docs.screenpipe.com/api-reference/database/execute-raw-sql.md): Execute a raw SQL query against the screenpipe database. Use with caution.
- [Add content to database](https://docs.screenpipe.com/api-reference/database/add-content-to-database.md): Manually insert screen or audio content into the database.
- [List unnamed speakers](https://docs.screenpipe.com/api-reference/speakers/list-unnamed-speakers.md): Returns speakers that haven't been identified/named yet.
- [Update speaker name](https://docs.screenpipe.com/api-reference/speakers/update-speaker-name.md)
- [Search speakers](https://docs.screenpipe.com/api-reference/speakers/search-speakers.md)
- [Delete speaker](https://docs.screenpipe.com/api-reference/speakers/delete-speaker.md)
- [Mark speaker as hallucination](https://docs.screenpipe.com/api-reference/speakers/mark-speaker-as-hallucination.md): Flag a detected speaker as a false positive / hallucination.
- [Merge speakers](https://docs.screenpipe.com/api-reference/speakers/merge-speakers.md): Merge two speaker identities into one.
- [Find similar speakers](https://docs.screenpipe.com/api-reference/speakers/find-similar-speakers.md)
- [Reassign speaker](https://docs.screenpipe.com/api-reference/speakers/reassign-speaker.md): Reassign audio segments from one speaker to another.
- [Undo speaker reassignment](https://docs.screenpipe.com/api-reference/speakers/undo-speaker-reassignment.md)
- [List meetings](https://docs.screenpipe.com/api-reference/meetings/list-meetings.md): Returns detected and manually started meetings with transcriptions.
- [Get meeting detection status](https://docs.screenpipe.com/api-reference/meetings/get-meeting-detection-status.md)
- [Merge meetings](https://docs.screenpipe.com/api-reference/meetings/merge-meetings.md)
- [Bulk delete meetings](https://docs.screenpipe.com/api-reference/meetings/bulk-delete-meetings.md)
- [Start a manual meeting](https://docs.screenpipe.com/api-reference/meetings/start-a-manual-meeting.md)
- [Stop a manual meeting](https://docs.screenpipe.com/api-reference/meetings/stop-a-manual-meeting.md)
- [Get meeting by ID](https://docs.screenpipe.com/api-reference/meetings/get-meeting-by-id.md)
- [Update meeting](https://docs.screenpipe.com/api-reference/meetings/update-meeting.md)
- [Delete meeting](https://docs.screenpipe.com/api-reference/meetings/delete-meeting.md)
- [List memories](https://docs.screenpipe.com/api-reference/memories/list-memories.md): Returns saved AI memories / knowledge extracted from screen activity.
- [Create memory](https://docs.screenpipe.com/api-reference/memories/create-memory.md)
- [Get memory by ID](https://docs.screenpipe.com/api-reference/memories/get-memory-by-id.md)
- [Update memory](https://docs.screenpipe.com/api-reference/memories/update-memory.md)
- [Delete memory](https://docs.screenpipe.com/api-reference/memories/delete-memory.md)
- [Merge video frames](https://docs.screenpipe.com/api-reference/experimental/merge-video-frames.md)
- [Validate media files](https://docs.screenpipe.com/api-reference/experimental/validate-media-files.md)
- [Search UI elements](https://docs.screenpipe.com/api-reference/elements/search-ui-elements.md): Search elements across all frames with optional FTS, time, and app filters.
- [Get activity summary](https://docs.screenpipe.com/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).
- [Get vault status](https://docs.screenpipe.com/api-reference/vault/get-vault-status.md): GET /vault/status
- [Lock vault](https://docs.screenpipe.com/api-reference/vault/lock-vault.md): POST /vault/lock
- [Unlock vault](https://docs.screenpipe.com/api-reference/vault/unlock-vault.md): POST /vault/unlock
- [Set up vault](https://docs.screenpipe.com/api-reference/vault/set-up-vault.md): POST /vault/setup
- [Initialize cloud sync](https://docs.screenpipe.com/api-reference/cloud-sync/initialize-cloud-sync.md): Initialize sync at runtime with credentials.
- [Get sync status](https://docs.screenpipe.com/api-reference/cloud-sync/get-sync-status.md): Get current sync status.
- [Trigger sync](https://docs.screenpipe.com/api-reference/cloud-sync/trigger-sync.md): Trigger an immediate sync.
- [Lock sync](https://docs.screenpipe.com/api-reference/cloud-sync/lock-sync.md): Lock sync (stop service and clear state).
- [Download synced data](https://docs.screenpipe.com/api-reference/cloud-sync/download-synced-data.md): Download and import data from other devices.
- [Push scheduled task configs to cloud](https://docs.screenpipe.com/api-reference/cloud-sync/push-scheduled-task-configs-to-cloud.md): Push local scheduled task manifest to cloud (merge with remote first).
- [Pull scheduled task configs from cloud](https://docs.screenpipe.com/api-reference/cloud-sync/pull-scheduled-task-configs-from-cloud.md): Pull scheduled task manifest from cloud, merge with local, apply to disk.
- [Configure retention policy](https://docs.screenpipe.com/api-reference/data-retention/configure-retention-policy.md): POST /retention/configure — enable/disable local retention, set days.
- [Get retention status](https://docs.screenpipe.com/api-reference/data-retention/get-retention-status.md): GET /retention/status — return current retention state.
- [Run retention cleanup now](https://docs.screenpipe.com/api-reference/data-retention/run-retention-cleanup-now.md): POST /retention/run — trigger an immediate cleanup run.
- [Delete data in time range](https://docs.screenpipe.com/api-reference/data-management/delete-data-in-time-range.md): Permanently delete all captured data (frames, accessibility text, OCR fallback text, audio, etc.) within a time range.
- [Delete device data](https://docs.screenpipe.com/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.screenpipe.com/api-reference/data-management/get-device-storage-usage.md): Get record counts per synced device.

## OpenAPI Specs

- [openapi](/openapi.yaml)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.