← back to the directory
Application Automation & IntegrationAgents & Orchestration

Self-Operating Computer

1Let 2models 3operate 4your 5computer 6visually.

the six Ws · specification

W1 Who

By OthersideAI.

W2 What

A framework letting multimodal models view the screen and control mouse and keyboard.

W3 Where

A Python app driving your desktop.

W4 When

When experimenting with computer-use agents.

W5 Why

An early, simple computer-use framework.

W6 With

Python and a multimodal model key.

W7 Watch

MIT open-source; controls your real machine, supervise it closely.

Computer-useVisionAutonomous

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.