screenpipe

screenpipe records screen activity and audio so your AI can use your work history as context. It runs on macOS, Windows, and Linux, with a local API and MCP server for connecting your agents.

screenpipe builds a timestamped, searchable history from on-screen text, app and window context, screen images, system audio, and microphone audio you choose to capture. Use it to find something you saw, reconstruct a day, recover a decision, or draft a follow-up. It cannot recall a period that was not successfully captured.

By default, capture, transcripts, and the search index stay on your device. Data leaves only when a feature you enable needs it, for example cloud AI, cloud sync, an export, a connector, or a team workflow. Each integration has its own destination: local-first does not mean every optional feature runs locally.

Yes. You can pause recording, use recording schedules, include or ignore apps and windows, ignore URLs, and set automatic retention. Privacy filters can redact sensitive text before it is stored, and DRM-protected content pauses capture by default. Review these settings before recording confidential work.

Any always-on capture uses CPU, battery, and disk. The load depends on your displays, capture quality, audio sources, and local transcription settings. screenpipe uses accessibility events, GPU capture, power tiers, compression, and retention controls to reduce that cost, but it is not zero. If the timeline has gaps, fix capture first. An AI summary cannot recover missing data.

screenpipe runs on macOS, Windows, and Linux. Its capture engine is public and source-available under the Screenpipe Commercial License, so you can inspect the code that handles your data, build it yourself, or run the CLI headless.

There is a free tier for trying local capture, AI search, and meeting notes. Paid plans add more history, AI usage, model choices, sync, and team controls. Check the pricing page for the current price, trial, limits, amount due today, and renewal terms before checkout; existing lifetime licenses keep working.

First, confirm that the timeline contains recent screen and audio history. Then retrieve one specific fact from the last hour, such as “what did I decide about the launch, and where did I say it?” Only connect a note, CRM, or other destination after that result is useful. This catches permission, capture, transcription, and search problems before they become unreliable automation.

Yes. MCP-compatible agents can query screenpipe, and developers can use the local REST API, SDK, CLI, or SQLite database. A connected agent gets the context it requests and your settings permit; screenpipe does not automatically send your entire archive with every prompt.

Yes. screenpipe can draft a meeting follow-up, daily or weekly review, or SOP from captured work. Review the results before running the task on a schedule or trigger. Keep external writes and sends behind approval until you are confident in the output.