Product Thumbnail

UI-TARS Desktop

Control your computer using natural language

Open Source
Artificial Intelligence
GitHub

A GUI Agent application based on https://github.com/bytedance/UI-TARS that allows you to control your computer using natural language. From Bytedance.

Top comment

Features 🤖 Natural language control powered by Vision-Language Model 🖥️ Screenshot and visual recognition support 🎯 Precise mouse and keyboard control 💻 Cross-platform support (Windows/MacOS) 🔄 Real-time feedback and status display

Comment highlights

Just tried using this for a workflow demo. It handled intricate scripting tasks with surprising accuracy. Could future versions possibly include custom command sets tailored by the user?
Wow I love it, controlling mouse & keyboard w/ natural language is pretty niche but I'm here for it! Top-hunt Chris, looking forward to seeing how the devs continue to develop this!!