UI-TARS Desktop

Active
GitHub TypeScript Apache-2.0

Description

ByteDance's open-source multimodal AI agent stack connecting cutting-edge AI models with agent infrastructure for GUI automation and computer control.

Key Features

  • Multimodal AI agent stack — Agent TARS + UI-TARS Desktop dual-project architecture covering CLI, Web UI, and desktop
  • GUI automation — Native desktop and browser control powered by the UI-TARS model
  • MCP tool integration — Seamless connection to external MCP servers for tool extensibility
  • Remote computer/browser control — One-click remote control of any computer or browser with zero config
  • Local/remote operator — Supports both local model and remote model operation modes
  • Sandbox execution — Dedicated AIO Agent Sandbox for isolated tool execution environments

Use Cases

💡 Automate web interaction tasks like booking, form filling, and data collection
💡 Cross-application GUI automation testing and quality assurance
💡 Control desktop applications via natural language instructions for complex workflows
💡 Build multimodal AI application prototypes requiring visual understanding

Tags

multimodal-agent gui-automation computer-use mcp typescript

Categories

🌐 Browser Agent 🤖 Agent Framework

Quick Start

# Install Agent TARS CLI
npm install -g @agent-tars/cli

# Launch Agent TARS
agent-tars
Visit GitHub Visit Website

Related Projects