agent-desktop: A Rust-based CLI for AI-driven desktop automation via OS accessibility trees
By
lahfir
A five-star bake. Worth schmearing, sharing, saving.
Summary
agent-desktop is a native desktop automation CLI built with Rust, designed specifically for AI agents to control desktop applications through OS accessibility trees. It provides structured JSON output and deterministic element references without relying on screenshots, pixel matching, or browser automation. The tool features 53 commands for observation, interaction, keyboard, mouse, notifications, and clipboard control, and is available as both a fast single-binary CLI and a C-ABI cdylib for integration with Python, Swift, Go, Ruby, Node, and C.
Key quotes
· 3 pulledagent-desktop is a native desktop automation CLI designed for AI agents, built with Rust.
It gives structured access to any application through OS accessibility trees — no screenshots, no pixel matching, no browser required.
53 commands: Observation, interaction, keyboard, mouse, notifications, clipboard.
You might also wanna read
NeuralAgent: AI Desktop Interface for Automated Computer Tasks
NeuralAgent is an AI-powered desktop interface that can perform human-like computer interactions including clicking, typing, scrolling, and
UseDesktop: Infrastructure Platform for Training Desktop AI Agents
UseDesktop is an infrastructure platform for training desktop agents, which are computer use agents designed to be more useful than traditio
Open Computer Use: Open-Source Desktop Automation Tool for AI Agents via MCP
Open Computer Use is an open-source tool that turns local desktop automation into a standard MCP (Model Context Protocol) service. It allows
OpenOwl: macOS Desktop Automation Agent for AI-Assisted Task Automation
OpenOwl is a macOS desktop automation agent that enables AI assistants (Claude, Codex, or MCP-compatible AIs) to perform screen-based automa
NeuralAgent: AI Assistant That Controls Your Computer Through Screen Interaction
NeuralAgent is a personal AI assistant that can operate an entire computer by seeing the screen and controlling the PC directly. Unlike chat
Agent Bar: Menu Bar Interface for Claude Code AI Projects
Agent Bar is a desktop application that provides a native menu bar interface for Claude Code, allowing users to interact with AI projects th
