Self-Operating Computer
Framework that lets a multimodal model view the screen and operate a computer with mouse and keyboard actions.
Agent by HyperWrite (OthersideAI)
IndexedMIT★ 10,294
Get started
Setup steps are in the repository. Website · Repository
About
Self-Operating Computer is a framework from HyperWrite (OthersideAI) that lets a multimodal model look at the screen and decide on a series of mouse and keyboard actions toward an objective. It is installed with pip and launched with the operate command, and the README lists support for OpenAI, Gemini, Claude 3, Qwen-VL and LLaVA through Ollama. It also has an optional voice input mode.
Use cases: other, browser-automation, workflow-automation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Jobs
- otherREADME
- Autonomy
- Autonomous: runs tasks end to end and reports backREADME
- Where you use it
- TerminalREADME
- Hosting
- You run itREADME
- Models
- gpt-4o, gpt-4.1, o1, gemini-pro-vision, claude-3, qwen-vl, llavaREADME
- Open source
- Yes
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.
Signals
- Stars
- 10,294
- Forks
- 1,410
- Open issues
- 83
- Last commit
- Oct 19, 2026 (9 days ago)
- Last release
- Feb 28, 2025 (1 year ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- READMEgithub-graphql
Cite this page
Self-Operating Computer. Agent Mart. https://agentmart.dev/agents/self-operating-computer (last updated 2026-10-24)