# screenpipe > AI agent memory. Local-first 24/7 capture of screen and audio, plus an open API any agent can query. > Full reference: https://screenpipe.com/llms-full.txt screenpipe is AI agent memory: it continuously captures what you've seen, said, and heard on your computer, and gives that context to whatever AI you already use, so it never starts from scratch. screenpipe runs in the background on macOS, Windows, and Linux. It captures your screen (all monitors), microphone, and system audio, extracts text via OCR and audio via on-device speech-to-text, and stores everything in a local SQLite database. From there it exposes a local REST API and MCP server that AI agents (Claude Code, Cursor, ChatGPT, custom pipes) can query for full context of what the user is doing, without the user having to re-explain their work history. The thesis: every AI agent needs to know what the user is doing, act on that context, and trigger without prompts. Vision is the universal interface; the screen is the highest-fidelity signal of human intent. screenpipe is the context infrastructure between the two. Built by screenpipe, backed by Y Combinator (S26). Source-available. screenpipe is local-first by design: in local-only mode, screen captures, audio transcriptions, and extracted text are stored on your device. Data movement depends on whether you enable sync, cloud AI, exports, connectors, or team workflows. ## What screenpipe does - **Record**: continuous screen capture (all monitors), system audio, and microphone, 24/7, in the background - **Rewind**: visual timeline of everything that happened on the device, queryable by app, window, URL, or natural language - **Ask**: natural-language search across OCR text and transcripts, with screenshots and audio clips returned alongside text - **Pipes**: extensible plugin system: TypeScript/Bash scripts that react to screen activity (meeting summaries, daily journals, CRM sync, custom workflows) - **API + MCP**: local HTTP API and Model Context Protocol server, so any AI agent can query the user's context ## How it differs from alternatives - **vs Rewind / Limitless**: source-available, auditable, and cross-platform; local-only deployment is available - **vs Microsoft Recall**: works today on macOS, Windows, and Linux; not gated to Copilot+ PCs; source-available and auditable - **vs Granola / Otter / Fireflies / tl;dv**: not just meetings, captures the entire desktop continuously, including browsing, docs, messaging, and code - **vs ChatGPT / Claude memory**: server-side memory features only remember chat content; screenpipe captures everything you actually do - **vs proprietary "memory" SaaS**: local-only deployment keeps captured data on-device; build custom workflows via the API and pipe SDK Compare pages: https://screenpipe.com/compare ## Who it's for - **Developers and AI engineers** building agents that need context of what the user is doing, via Claude Code / Cursor / Cline integrations, custom MCP servers, autonomous workflows - **Knowledge workers** who want their AI assistants to know what they were doing five minutes ago without describing it - **Enterprises** with compliance / data-residency / sovereignty requirements that rule out cloud memory tools - **Researchers and indie hackers** who want a programmable layer over their own digital life ## Technical surface - **Platforms**: macOS (Apple Silicon + Intel), Windows 10/11, Linux - **Capture**: native OCR (Apple Vision on macOS, Windows OCR API, Tesseract on Linux); on-device transcription (Parakeet-MLX on Apple Silicon, Whisper.cpp elsewhere; optional Deepgram cloud) - **Storage**: local SQLite + WAL; configurable retention; ~5-10 GB / month typical - **API**: a local REST API plus a local MCP server consumable by Claude Desktop, Cursor, Continue, etc. - **Pipes SDK**: write plugins as `pipe.md` files with embedded `bash` / `bun` blocks; runs sandboxed in the user's environment - **Performance target**: <20% CPU, <3 GB RAM on release builds, designed to run forever in the background ## Links - [Homepage](https://screenpipe.com/): product overview - [Onboarding / Download](https://screenpipe.com/onboarding): get the app - [Compare](https://screenpipe.com/compare): vs Rewind, Limitless, Microsoft Recall, Granola, Otter, tl;dv, etc. - [AI Integrations](https://screenpipe.com/integrations): setup guides for connecting screenpipe context to AI tools - [Claude Integration](https://screenpipe.com/integrations/claude): connect Claude Desktop and Claude Code through MCP - [Codex Integration](https://screenpipe.com/integrations/codex): connect the Codex app and CLI through MCP and screenpipe skills - [AI Second Brain](https://screenpipe.com/ai-second-brain): automatic local-first context for AI agents - [Personal Wiki](https://screenpipe.com/personal-wiki): a personal wiki that builds itself by capturing what you see and read locally - [Pipes](https://screenpipe.com/pipes): plugin marketplace - [SDK](https://screenpipe.com/sdk): building on top of screenpipe - [Enterprise](https://screenpipe.com/enterprise): on-prem / SSO / data-residency - [Privacy Filter](https://screenpipe.com/privacy-filter): PII redaction layer (Tinfoil) - [Security](https://screenpipe.com/security): threat model, encryption, audit posture - [Changelog](https://screenpipe.com/changelog): releases - [Research](https://screenpipe.com/research): technical posts - [Blog](https://screenpipe.com/blog): announcements and tutorials - [Privacy Policy](https://screenpipe.com/privacy) - [Terms](https://screenpipe.com/terms) - https://screenpipe.com/blog/how-to-turn-off-otter-ai — How to Turn Off Otter AI: What to Use Instead ## Source code and community - GitHub: https://github.com/screenpipe/screenpipe (21,000+ stars as of 2026-08) - Documentation: https://docs.screenpi.pe - Discord: https://discord.gg/screenpipe - X: https://x.com/screenpipe - LinkedIn: https://www.linkedin.com/company/screenpipe - Contact: support@screenpi.pe ## Licensing The source is available under the Screenpipe Commercial License. Personal, non-commercial, educational, research, and limited evaluation use is free; commercial use requires a paid license. Official builds are governed separately by the app license and subscription terms. Basic includes efficient hosted models and AI credits; higher plans add frontier models, sync, greater capacity, team features, and managed deployment.