Enables AI assistants to observe and interact with desktop graphical user interface windows on Windows.
Sponsored
Empower AI assistants with advanced desktop GUI interaction capabilities on Windows. This tool leverages the Model Context Protocol to provide AI with 'vision' through screenshots and element detection, and 'control' via clicks, text input, and keyboard shortcuts. It facilitates robust GUI automation by allowing AI to see, find, and interact with elements on background windows, enabling sophisticated workflows without interrupting the user's focus. It also offers a Rust library for deterministic scripting of AI-discovered workflows.
주요 기능
01Find and click UI elements using image template matching (NCC)
02Operate on background windows without stealing focus or switching context
03Capture screenshots and rapid multi-frame bursts of windows
04Type text, send keyboard shortcuts, and manage clipboard content
050 GitHub stars
06AI vision and control of Windows desktop GUI applications
사용 사례
01Translating AI-discovered GUI workflows into deterministic Rust automation scripts
02Building reusable UI element template libraries for adaptive GUI automation
03AI-driven desktop automation and interactive control of Windows applications
