lahfir/agent-desktop
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.
About the project
Rust CLI that lets AI agents control desktop apps via macOS accessibility trees, with stable element refs and a snapshot-to-action loop. Combines a native binary with a C-ABI cdylib for Python/Swift/Go/Node bindings.
Useful for
- Drive Slack or Xcode from an agent via snapshots and ref-based clicks
- Cut token usage on dense UIs using skeleton traversal before acting
- Open a CDP port to control Chromium app content with Playwright
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 3 stars so far today, about 10 expected by the end of the day.
- GitHub Trending Rust today: #17, +14 stars.
- Recent forks include notable developers: @Reamd7 (211 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 1,278
- Stars in a day
- 10
- Forks
- 86
- Issues and pull requests
- 203
- Watchers
- 7
- Language
- Rust
- License
- Apache-2.0
- Latest release
- v0.9.2 · September 17, 2026
- Created
- February 19, 2026
- Last push
- September 17, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 19, 2026GitHub Trending Rust today: #17, +14 stars
Similar projects
-
9.4
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.
-
8.2
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…
-
8.2
latent-spaces/brag
An agent skill (Claude Code, Codex, opencode, etc.) that turns a project you just built into a short launch video with music, motion, and share copy — in one command. Rendering is powered by Hyperframes.
-
7.3
trycua/cua
Open-source toolkit for computer-use agents: cloud and local desktops, an app automation driver, and benchmarks for training and evaluation. For those giving AI agents control of a computer.
-
7.2
Tencent/BrowserSkill
BrowserSkill connects AI agents (Cursor, Claude Code, Codex, etc.) to your already logged-in browser via the bsk CLI and an extension, letting the agent work in a separate window without interrupting you.
-
7.0
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.