Agent Desktop gives any agent reliable computer use on the desktop. Built with Rust, it sees any app's real UI structure through OS accessibility trees and operates it — refs stay stable and actions stay safe to retry, instead of guessing from pixels.
agent-desktop is a command-line tool that lets AI agents inspect and control desktop applications through operating-system accessibility data instead of screenshots or pixel matching. It is used to automate applications such as Finder, Safari, Xcode, and Slack with structured JSON commands and results.
Latest release v1.0.1 · 28 Oct 2026
1 file for Codex and OpenCode: agent-desktop AGENTS.md — 5,132 tokens loaded in every session.
AGENTS.md A 5,132 tok These files are lahfir/agent-desktop's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.