Screenpipe

Screenpipe captures screen text and audio locally to build searchable computer history. It helps users recall what they saw or heard, find past conversations, and generate meeting notes and work summaries. Its [MCP server](https://github.com/screenpipe/screenpipe/tree/main/packages/screenpipe-mcp) and local API let compatible AI assistants retrieve this context for tasks such as researching earlier work or preparing a recap.

Raw capture is stored locally by default. Configured cloud AI, transcription, sync, integrations and connected AI clients can transmit context off-device. Screenpipe is source-available under the [Screenpipe Commercial License](https://github.com/screenpipe/screenpipe/blob/main/LICENSE.md). [Source](https://github.com/screenpipe/screenpipe) · [Pricing](https://screenpipe.com/onboarding)

Gives an agent memory of what you actually worked on — useful context for recaps, research and meeting notes.