Screenpipe
PulseGate's liveness check found it on 3 Oct 2026; it has been in the index since 29 Aug 2026. How this is checked
Screenpipe is an open-source local computer-history system that continuously records screen activity and makes the resulting context available to AI agents. It provides desktop capture, searchable history, and developer interfaces for building context-aware agent workflows.
Inferred · not functionally tested
Overview
6 featuresPurpose: Giving AI agents access to a user's locally recorded computer history and context.
Inferred · not functionally tested
Audience: developers building context-aware AI agents
Inferred · not functionally tested
Functions: rag, agents, data_extraction
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: unknown · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Open Source · platforms: DESKTOP, API · deployment: macos, windows, linux, self_hosted, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: github.com. These links do not verify the individual claims.
In the Memory & skills space, Screenpipe takes a focused approach. Inferred · not functionally tested: It focuses on giving AI agents access to a user's locally recorded computer history and context. Inferred · not functionally tested: It is built as an open-source project for developers building context-aware AI agents. Basis unknown · not verified: Screenpipe is open source under the Open Source license. Basis unknown · not verified: It ships for macOS, Windows, Linux, and API, and it can be self-hosted.
screenpipe builds and maintains Screenpipe. Inferred · not functionally tested: Among its 6 catalogued features are continuous recording, local storage, and screen capture. Inferred · not functionally tested: Catalogued interfaces include a public API and an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Continuous recording
- Local storage
- Screen capture
- Searchable history
- Agent context
- API access
Topics: Inferred · not functionally tested
Built with & integrations
- openai
- dall- in the HTML
- local_oss
- bollama in the HTML
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed29 Aug · 03:08 UTCscreenpipe seen via MCP Registry (official)Source: MCP Registry (official) · Open
Frequently asked questions about Screenpipe
- What is Screenpipe?
- Inferred · not functionally tested: Screenpipe focuses on giving AI agents access to a user's locally recorded computer history and context. It is catalogued under Memory & skills on PulseGate.
- Who should use Screenpipe?
- Inferred · not functionally tested: Screenpipe is an open-source project built for developers building context-aware AI agents.
- Is Screenpipe free?
- Basis unknown · not verified: Yes — Screenpipe is open source under the Open Source license and free to use.
- What platforms does Screenpipe run on?
- Basis unknown · not verified: Screenpipe runs on macOS, Windows, Linux, and API. It can also be self-hosted.
- Is Screenpipe still active?
- PulseGate's liveness check found it on 3 Oct 2026.
- Who develops Screenpipe?
- Screenpipe is developed by screenpipe.
- Is Screenpipe open source?
- Basis unknown · not verified: Yes — Screenpipe is open source under the Open Source license.
- Does Screenpipe have an API or integrations?
- Inferred · not functionally tested: Yes — Screenpipe exposes a public API and an MCP server.
Similar projects
Closest matches by what these projects do