Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
36kstars
3.6kforks
TypeScript
agentagent-tarsbrowser-usecomputer-usecoworkgui-agentgui-operatormcpmcp-servermultimodaltarsui-tars
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
TARS is an open-source multimodal AI agent stack designed to enable human-like task completion across terminals, computers, and browsers by integrating advanced AI models and various real-world tools.
Use this when
- Automating complex tasks across desktop, browser, and terminal.
- Developing AI agents that interact with graphical user interfaces.
- Integrating vision capabilities into AI task workflows.
- Need an AI agent to control remote computers or browsers.
- Creating AI agents that utilize multiple real-world tools.
Don't use when
- Only need basic, non-AI scripting or robotic process automation.
- Require a very lightweight automation solution without agent logic.
Capabilities
- Multimodal AI agent foundation
- GUI, vision, and terminal interaction
- CLI and Web UI for agent control
- Remote computer and browser operation
- SDK for building automation agents
InstallMCPRun via npx (Node)
Universal installANY TOOL
$ npx skillcity@latest bytedance/UI-TARS-desktopAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.
Requires Node.js 18+ (ships with npx).
Or install manually
npx -y ui-tars-desktop
MCP Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"ui-tars-desktop": {
"command": "npx",
"args": [
"-y",
"ui-tars-desktop"
]
}
}
}Readme
Loading README…