Home› Projects› agent-desktop
agent-desktop
Rust

agent-desktop

Computer use CLI for AI agents

by vercel-labs · GitHub
Stars
Forks
License
Created
Last commit
Language
Likely
Self-hostable
accessibilityaccessibility-apiai-agentsApache-2.0RustSelf-hostable
View on GitHub
In plain words

Control desktop applications on your computer using AI agents that can interact with the user interface without needing images.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
agent-desktop — GitHub preview card
📈 Star history
14 94714 946
2026-11-052026-11-06
📈 Track agent-desktop

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Computer use CLI for AI agents

agent-desktop has 14.9k stars on GitHub. It has been forked 1k times. agent-desktop is written mainly in Rust. It has been in active development since 2026. agent-desktop is available under the Apache-2.0 license. Its main topics are accessibility, accessibility-api, ai-agents, automation.

❓ Frequently asked questions

What is agent-desktop?

Computer use CLI for AI agents

Is agent-desktop open source?

agent-desktop is an open-source project. It is released under the Apache-2.0 license.

Is agent-desktop free?

Yes. agent-desktop is free and open source — you can use, modify and self-host it.

What license does agent-desktop use?

agent-desktop is available under the Apache-2.0 license.

What language is agent-desktop written in?

agent-desktop is written mainly in Rust.

🏅 Maintainer of this project?
olud.ai badge — agent-desktop

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=vercel-labs-agent-desktop)](https://olud.ai/project/vercel-labs-agent-desktop.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.