Tool not found.
Back to Home
Source-available screen and audio history for recall, meeting notes, and work summaries, with a local API and MCP server for compatible AI tools.
screenpipe is a source-available desktop memory and automation platform that continuously captures screen activity, audio, accessibility data, OCR text, and application context to create a searchable personal activity timeline. It's positioned as a local-first alternative to tools like Rewind AI, Microsoft Recall, Granola, and Otter.ai. Raw history is stored locally on the user's device by default, though configured cloud AI, transcription, sync, and third-party integrations can transmit context off-device. Built with Rust, Tauri, TypeScript, and SQLite, the platform runs on Windows, macOS, and Linux with event-driven screen capture optimized for low CPU and storage usage. screenpipe supports local Whisper speech transcription, accessibility tree extraction, OCR fallback processing, AI-powered semantic search, MCP server integration for AI assistants like Claude and Cursor, REST APIs, and plugin-based automation agents called Pipes. The code is source-available under the Screenpipe Commercial License, which permits personal, non-commercial use; commercial use requires a paid license.
