bytedance/UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Supports local and remote desktop/browser automation through the UI-TARS vision model, enabling agents to execute GUI interactions by understanding screenshots and generating precise control commands. Integrates with Model Context Protocol (MCP) tools for extended capabilities, while offering both CLI and Web UI interfaces with streaming tool execution, runtime timing statistics, and isolated sandbox environments for safe task execution.
28,739 stars. Actively maintained with 2 commits in the last 30 days.
Stars
28,739
Forks
2,814
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Commits (30d)
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/bytedance/UI-TARS-desktop"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.