Records screen and audio locally, then indexes that content into a searchable database for retrieval and AI-driven automation. Adoption is appropriate when local-first storage is acceptable and commercial use requirements are reviewed.
Project overview
Records screen and audio locally, then indexes that content into a searchable database for retrieval and AI-driven automation. Adoption is appropriate when local-first storage is acceptable and commercial use requirements are reviewed.
Project type
AI Agent · AI Search · Data Processing
Use cases
Meeting Notes · Knowledge Q&A · Automation
Deployment
Refer to project documentation
License
License pending
Best for
General users and enterprise teams that require a personal knowledge base of computer activity maintained in local storage rather than the cloud.
Developers needing a local REST API and SDK to build custom searches across screen content and audio recordings.
Key capabilities
Captures screen and audio by listening for meaningful OS events like app switches and typing pauses, pairing screenshots with the accessibility tree and falling back to OCR.
Real-time speech-to-text using local Whisper or cloud Deepgram with speaker identification.
Full-text and natural language search across accessibility text, OCR, and transcriptions using SQLite FTS5.
Visual DVR-like timeline to scroll through screen history and playback audio.
Scheduled AI agents defined as markdown files that query screen data and take actions based on work activity.
Runs as an MCP server allowing AI assistants to query screen history.
Local REST API and JavaScript/TypeScript SDK for searching screen content and audio.
Limitations and risks
Source-available under a commercial license; personal, non-commercial use is permitted, but commercial use requires a license.
Linux requires building from source.
Product analytics through PostHog and crash diagnostics via Sentry are enabled by default.
Commercial use of the source requires a paid license.
Getting started
Download the desktop app for an auto-updating experience, or run directly via npx without manual build steps.
Evidence and sources
GitHub project description: Record how you work and turn that into agents. Local, private, secure.
Release: Screenpipe App v2.5.112
README: screenpipe turns your computer into a personal AI that knows everything you've done. record. search. automate. all local, all private, all yours
README: never forget what you saw, heard, or did
README: It captures what you see, say, and do, locally, then turns real work into searchable memory, SOPs, and automations for AI agents.