跨平台桌面AI操控工具agent-desktop发布
Start here
2026年11月3日,面向AI Agent的跨平台桌面操控工具agent-desktop正式发布。该工具提供命令行界面与C库,旨在通过桌面应用的无障碍树读取UI状态并返回JSON格式数据,仅支持原生桌面应用且不做纯像素匹配。agent-desktop本身不内置AI模型,主要通过为界面可操作元素分配ref标识,供外部脚本调用并完成“观察-操作-验证”的操作闭环。目前该工具已实现跨平台支持macOS、Windows和Linux系统,并统一提供60个基础操作命令。
AI-generated from reports · Updated 2 days ago
Report timeline
Follow the reports to see different sides of the story.
- Hacker News · AISelectedagent-desktop Released: A Cross-Platform Desktop Accessibility Tree Control CLI for AI Agents
agent-desktop has been released as a CLI and C library tool that enables AI agents to inspect desktop application UIs via accessibility trees and return structured JSON. The tool includes no built-in models; instead, it assigns refs to actionable elements, allowing external scripts to close the "observe-act-verify" loop. It focuses solely on native desktop apps without relying on raw pixel matching. With cross-platform support for macOS, Windows, and Linux, it provides a unified set of 60 basic action commands.
Story heat trend
Current heat 4·Comparable peak 10(Nov 3 14:00)·Comparable change, last 24 hours-50%
Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.