lahfir/agent-desktop
Native desktop automation CLI for AI agents. Control any application through OS accessibility trees with structured JSON output and deterministic element refs.
Implemented as a single Rust binary with 50+ commands, it uses accessibility trees exclusively rather than screenshots, offering 15-step AX-first interaction chains that exhaust native APIs before falling back to mouse events. The snapshot + deterministic ref workflow (`@e1`, `@e2`) optimizes for LLM reasoning by enabling stable element selection across UI changes without re-querying the tree. Distributes via npm with zero runtime dependencies and supports macOS 13.0+ applications from Finder to Xcode through a JSON command/response protocol with machine-readable error codes.
Stars
32
Forks
3
Language
Rust
License
—
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/lahfir/agent-desktop"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
open-webui/open-terminal
A computer you can curl ⚡
pproenca/agent-tui
TUI automation for AI agents. Control any terminal app from code.
AI-Shell-Team/aish
Empower the Shell to think. Evolve Operations.
makefinks/daemon
Terminal AI agent with a sci-fi avatar: OpenTUI interface, text/voice, hotkey-driven
VritraSecz/VritraAI
🚀 Next-gen AI terminal shell: command explanations, code analysis, security scanning, 37 themes,...