guictl

Level FSource

Lets AI agents see and control a desktop GUI: screenshots, OCR, mouse, keyboard, windows and accessibility-tree UI elements. One-shot JSON CLI or MCP server. Windows 10/11, and Linux on KDE Plasma 6 or GNOME 45+ (Wayland).

⭐ 1Browser AutomationRustRepo ↗Updated 2026-11-10

Installation

View source repo →

Related servers

Scrapling⭐ 101k · Browser Automation🕷️ The BEST Web Scraping framework that handles everything from a single requestChrome DevTools MCP⭐ 55.1k · Browser Automation谷歌官方：让 AI 操控 Chrome——页面操作、Lighthouse 性能分析、网络监控、控制台日志UI-TARS-desktop⭐ 39.6k · Browser AutomationThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models andPlaywright MCP⭐ 39.5k · Browser Automation微软出品的浏览器自动化工具，用结构化快照操控网页：点击、填表、截图、抓取，无需视觉模型cua-driver⭐ 32.1k · Browser AutomationRust-backed Cua Driver SDK and bundled executable for client applicationscua-s1⭐ 32.1k · Browser AutomationResearch tools for small, specialist computer-use models