agent-desktop
Apache-2.0 desktop computer-use CLI — OS a11y refs, not pixels
AI Agents / Browser Automation · Apache-2.0 · 1.8k
Reviewed 2026-09-30 · last push 2026-10-19 · repo checked 2026-10-19
What's Good
Apache-2.0 (lahfir/agent-desktop). Rust CLI + C-ABI cdylib; progressive skeleton snapshots (claimed ~78–96% token cuts on dense UIs); ref-based click/type; headless-by-default a11y actions; CDP launch path so Playwright/agent-browser can drive Chromium apps while native chrome stays on a11y. npm `agent-desktop` / npx; ClawHub + skills.sh listings.
The Catch
Production a11y drive is macOS-first — Windows/Linux a11y and input still Planned in the support matrix (cdylib ships wider). Vs agent-browser (Vercel Labs browser CDP/a11y refs): agent-browser is the web/browser CLI; agent-desktop is native desktop apps via OS accessibility. Needs Accessibility (+ Screen Recording/Automation for some features); do not hand it a logged-in machine without a sandbox story.
Verdict
Apache desktop computer-use when agents must drive native macOS apps by a11y refs — not agent-browser’s web CDP lane; Win/Linux still catching up.
Embed
Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.
Markdown
[](https://stackgems.com/gems/agent-desktop)
HTML
<a href="https://stackgems.com/gems/agent-desktop"><img src="https://stackgems.com/badge/agent-desktop.svg" alt="agent-desktop reviewed on Stack Gems" height="20"></a>
Related
AI Agents →- StagehandAI-native browser automation that mixes code and natural language
- Browser UseOpen-source framework for LLM-driven browser agents
- Playwright MCPOfficial Microsoft MCP server for Playwright browser automation
- Chrome DevTools MCPOfficial Chrome DevTools as an MCP server for coding agents
- agent-browserVercel Labs Rust CLI with compact a11y refs for agents