Screenpipe turns your computer into a personal AI memory system. Built in Rust with Tauri for the desktop app, it captures screen activity and audio using an event-driven architecture that only stores frames when something actually changes — consuming just 5-10 GB per month and 5-10% CPU on modern hardware. Text extraction primarily uses the OS accessibility tree for structured data (buttons, labels, text fields), falling back to OCR when needed. All data stays in a local SQLite database with FTS5 full-text search.
The platform's plugin system called 'Pipes' enables AI agents defined as simple markdown files to run on schedules, querying your captured data via the screenpipe API to perform automated tasks. Over 50 community-built pipes handle meeting notes, CRM updates, time tracking, expense management, and code context retrieval. Screenpipe also runs as an MCP server, allowing Claude Desktop, Cursor, and other AI assistants to directly query your screen history using natural language.
With 17,600+ GitHub stars and recognition on both Hacker News and Product Hunt, Screenpipe has positioned itself as the open-source alternative to Rewind.ai. The core engine is MIT-licensed and free, while the desktop app is a one-time $400 lifetime purchase. It supports macOS, Windows, and Linux with multi-monitor capture, speaker identification, PII redaction, and compatibility with any AI model — local, cloud, or self-hosted.