Sign in Submit site

Screenpipe

github.com/screenpipe/screenpipe Desktop & OS Privacy Open-source project

Screenpipe records screen activity locally and provides that context to AI agents.

Visit Screenpipe
github.com/screenpipe/screenpipe
Screenpipe homepage screenshot

About Screenpipe

Screenpipe is a source-available tool that continuously records computer work — screen and audio — and keeps that history on the device by default, then makes it usable by AI. It captures the full accessibility tree with OCR as a fallback, plus transcription, speaker information, keyboard inputs and app switches. The resulting history can be searched in natural language, used to map workflows and find work worth automating, and supplied to AI agents through an MCP server or CLI, including Claude Code, Codex, Gemini CLI and Cursor.

It is available as a desktop app for macOS, Windows and Linux, or through CLI commands such as npx screenpipe record and npx screenpipe setup. Capture filters cover windows, apps, Chrome extensions, passwords and a PII model, and encryption at rest is optional. Local capture and search work offline after setup, while cloud AI, sync and connected services require network access. Available features depend on the plan.

Key features

  • Continuous local screen and audio capture stored on the device by default
  • Captures accessibility tree, OCR fallback, transcription, speakers, keyboard inputs, app switches
  • Natural language AI search over recorded history
  • Maps workflows and surfaces work worth automating
  • MCP server and CLI that give coding agents recorded context
  • Filters for windows, apps, extensions, passwords; optional encryption at rest
Best for: Teams and individuals who want a locally stored, searchable record of computer work that can be handed to AI agents or used to identify automation opportunities.
Good for
  • Local-first design keeps capture history on the device by default
  • Source-available, so the code can be inspected, modified and audited under the license
  • Sets up MCP and skills for coding agents through a single CLI command
Watch out for
  • Cloud AI, sync and connected services require network access
  • Available features depend on the plan
  • Storage needs vary with activity, displays, audio, settings and retention, and should be measured on a representative day

Screenpipe at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Not stated
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026
machine learningllmcomputerspeech

Popular in Desktop & OS Privacy

Well-known listings from the same topic.

All 61
wBlockapps.apple.com/app/wblock/id6746388723uBO Lite Safariapps.apple.com/app/ublock-origin-lite/id674534…Stayapps.apple.com/app/stay-for-safari/id1591620171Lockdown Privacylockdownprivacy.comTor Browsertorproject.orgFirejailfirejail.wordpress.com
Related topicsSecurity ToolsVPNsPrivate EmailWebsite & URL ScannersAd & Tracker BlockersSecurity ResearchPrivacy GuidesPassword Managers

Screenpipe FAQ

Where is the recorded data stored?
Capture history stays on the device by default. Cloud AI, sync, integrations and managed team storage use separate data paths, which the project points to in its Privacy and security documentation.
Does Screenpipe work offline?
Local capture and search work offline after setup. Cloud AI, sync and connected services require network access.
How much CPU, memory and storage does capture use?
Capture is described as roughly 5-20% CPU and around 0.5-3 GB RAM, with local models and additional workloads using more. Storage depends on activity, displays, audio, capture settings and retention.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing

Listing maintained by Chris McClure and the WebIndexly editors · Updated Oct 11, 2026 · How we rank