READMEmain
No README available
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
UI-TARS-desktop
by alaa-nadi alaa-nadi/UI-TARS-desktop
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
More OS Automation MCP servers
Similar servers from the same category.
Playwright Browser Automation
markbustamante77
Enables browser automation through structured accessibility snapshots for web navigation, form-filling, and tab management without requiring vision-tuned models.
Cloudflare Browser Rendering
cloudflare
Browser automation for Cloudflare Workers and quick browser actions.
Scrapybara (Virtual Ubuntu)
scrapybara
Provides a bridge to virtual Ubuntu desktops for browsing the web, running code, and automating tasks through a sandboxed environment with bash command execution and natural language control.
CUA MCP Server
trycua
Enables LLMs to run Computer-Use Agent (CUA) workflows on Apple Silicon macOS.