screenpipe

Local-first recorder that turns your screen and audio history into searchable context for AI agents.

Visit Website ↗ by Screenpipe (Mediar, Inc.)

What is screenpipe?

Screenpipe continuously records your screen and audio to build a searchable, AI-powered memory of everything you do on your computer. It is the leading open-source-style alternative to Rewind.ai, Microsoft Recall, Granola and Otter.ai. By default everything stays on your device, and your approved AI agents can query that history through an MCP server or REST API to draft follow-ups, summaries and automations from real work.

Key features

  • Event-driven screen capture (screenshots only when something changes)
  • Audio capture with on-device transcription
  • Timestamped, searchable timeline of screen, audio and app context
  • Automatic meeting notes: summary, action items, decisions
  • Agent 'pipes' that trigger follow-ups and automations from captured work
  • MCP server plus local REST API, SDK, CLI and SQLite access
  • Local-first data with privacy filters and PII redaction
  • Team deployment with managed devices, SSO/SAML and audit trails

Pros

  • Data stays local by default, unlike cloud-based memory tools
  • Agents can search real work history instead of asking for context
  • Free tier covers trying local capture, AI search and meeting notes
  • Inspectable source and self-hostable for privacy-conscious users

Cons

  • Always-on capture costs CPU, battery and disk (roughly 5-10 GB per month)
  • Source-available under a commercial license, not fully open source
  • Workplace deployments need employee consent and recording-law review

screenpipe at a glance

PricingFreemium
CategoryAutomation & Agents
Platformswindows, macos, linux, api
CompanyScreenpipe (Mediar, Inc.)
Official websitescreenpi.pe
screen-recordingai-memoryai-agentsmeeting-noteslocal-firstmcpprivacyproductivity

How to choose the right Automation & Agents tool

Automation and agent tools promise to do work for you, so judge them on reliability before cleverness. Map the exact workflow you want to automate, then check the tool's integrations cover every app in that chain — one missing connector breaks the whole flow. Look for clear triggers, sensible limits, and logs you can read when something goes wrong, because something eventually will. For agents that act on your behalf, approval controls matter: you should be able to review messages, purchases or changes before they happen, especially at the start. Pricing usually scales with runs or tasks, so estimate your monthly volume honestly. Start with one low-risk workflow, measure the time it truly saves, and expand from there.

Compare all Automation & Agents tools →

screenpipe FAQs

What is screenpipe?

Screenpipe continuously records your screen and audio to build a searchable, AI-powered memory of everything you do on your computer. It is the leading open-source-style alternative to Rewind.ai, Microsoft Recall, Granola and Otter.ai. By default everything stays on your device, and your approved AI agents can query that history through an MCP server or REST API to draft follow-ups, summaries and automations from real work.

What are the main features of screenpipe?

screenpipe offers Event-driven screen capture (screenshots only when something changes), Audio capture with on-device transcription, Timestamped, searchable timeline of screen, audio and app context, Automatic meeting notes: summary, action items, decisions, Agent 'pipes' that trigger follow-ups and automations from captured work, MCP server plus local REST API, SDK, CLI and SQLite access, Local-first data with privacy filters and PII redaction and Team deployment with managed devices, SSO/SAML and audit trails.

How much does screenpipe cost?

screenpipe follows a freemium model: a free tier is available, and paid plans unlock higher limits and advanced features. Check its official website for current plan prices.

What are the pros and cons of screenpipe?

Strengths of screenpipe include Data stays local by default, unlike cloud-based memory tools; Agents can search real work history instead of asking for context; Free tier covers trying local capture, AI search and meeting notes. On the downside, Always-on capture costs CPU, battery and disk (roughly 5-10 GB per month); Source-available under a commercial license, not fully open source; Workplace deployments need employee consent and recording-law review.