s
screenpipe
YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)
open-sourcetool-integration
21.8k
Stars
+1815
Stars/month
2832
Commits (90d)
10
Releases (6m)
Star Growth
+5.4k (33.3%)estimated from velocity
Overview
Screenpipe continuously captures your screen, audio, and inputs locally to provide context to AI agents like Claude and Codex. It enables agents to work based on your actual computer activity and allows natural language search of your history. The tool is source-available and runs 100% locally on your machine.
Deep Analysis
Key Differentiator
Provides continuous local screen capture specifically to power AI agents with real-time user context.
⚡ Capabilities
- • Continuous local screen recording
- • Audio and input capture
- • Natural language search of history
- • Agent context provisioning
- • Local data storage
🔗 Integrations
ClaudeCodexOpenclawHermesRunnerMCP protocol
✓ Best For
- ✓ Providing real-time screen context to coding agents
- ✓ Creating agents that respond to user activity
- ✓ Local knowledge base of computer work
✗ Not Ideal For
- ✗ End-user AI applications
- ✗ Cloud-based agent platforms
- ✗ Generic screen recording without AI integration
⚠ Known Limitations
- ⚠ Requires local installation
- ⚠ 5-10% CPU usage during capture
- ⚠ ~20GB storage per month
Alternatives
S
Self-Operating Computer
A framework to enable multimodal models to operate a computer.
B
Browser Use Web UI
🖥️ Run AI Agent in your browser.
R
Robotgo
RobotGo, Go Native cross-platform RPA, GUI automation, Auto test and Computer use @vcaesar
C
Cua
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
Works with screenpipe
Tools that integrate with screenpipe, often used together in the same stack.
Compare screenpipe
Maintain screenpipe?
Show your live rank in your README, or put screenpipe in front of every visitor to AgentoolRank.