#655 · Primary category： AI Agents & Automation
agent-desktop
Native desktop automation CLI for AI agents. Control any application through OS accessibility trees with structured JSON output and deterministic element refs.
Project last updated：08/30/26
GitHub Stars
1.0K
Forks
69
Contributors
7
License
Apache-2.0
Why we included this project
AI agents that need to operate real desktop software often end up fighting with screenshots and pixel matching, which is fragile. agent-desktop sidesteps that by reading the operating system's accessibility tree and exposing any application's UI as structured JSON with deterministic element references, so an agent can act on the same controls a human would. The Rust CLI ships as a single binary with no runtime dependencies, and a C-ABI library lets you load it in-process from Python, Swift, Go, or other runtimes rather than forking a process for every call. It also works as an MCP server, so it drops into existing agent tooling with little setup. For teams automating macOS workflows, this is a dependable, non-visual way to control desktop apps.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.