Skip to main content
SC

Local computer history that gives AI agents searchable work context

screenpipe continuously captures screen activity, app context, and audio on your computer, then makes that history available to approved AI agents. It can support context-aware follow-ups and automations through a local API, MCP server, and connections to workplace tools.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 21 September 2026.

Open Source
Desktop
API
Memory
B2B
MCP Support
On-Device / Edge
Visit screenpipe

Is this your tool? Claim this listing to manage your content and analytics.

Ask about screenpipe

Get answers based on screenpipe's actual documentation

Try asking:

About

What It Is

screenpipe is an on-device memory and context layer for AI agents. It records what you see, say, and hear across your desktop—using accessibility context, screen frames with OCR, and transcribed microphone and system audio—so an AI can refer to your...

What to Know

The local-first design is the central differentiator: screenpipe says raw history stays on the device by default, and it provides controls to exclude apps, windows, URLs, and sensitive fields before storage. Its portable local database and API may...

Key Features
Captures screen activity, application context, microphone audio, and system audio locally on macOS, Windows, and Linux
Indexes screen frames with OCR, accessibility data, and audio transcripts for searchable work-history context
Exposes captured history through a local REST API and an MCP server
Lets users exclude selected apps, windows, URLs, and sensitive fields before local storage
Runs event-triggered agent workflows, such as creating meeting notes when a meeting ends
Use Cases
Ask an AI agent to update Linear tickets using evidence from the week’s work, linked pull requests, and Slack feedback
Generate a meeting summary with decisions and assigned action items, then save it to a local notes folder or Notion
Find details from earlier calls or desktop activity, such as who discussed pricing or what was agreed with a customer
Agenticness: Adaptive Collaborator

Proposes and executes multi-step plans with your approval.

High evidence
Last evaluated: Sep 21, 2026

Dimension Breakdown

Action Capability
Autonomy
Planning
Adaptation
State & Memory
Reliability
Interoperability
Safety
Operator Sovereignty

Categories

Details
AddedSeptember 21, 2026
RefreshedSeptember 21, 2026
Quick Facts
DeploymentOn-device / local
AutonomySemi-autonomous
Model supportSupports local models
MCP supportYes
Team supportEnterprise
Pricing modelFreemium
Interfacegui, api
Sources
Last updated September 21, 2026
Free daily brief

When screenpipe changes its pricing, we catch it the next morning

We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.

I use AI for: