Skip to main content
ClaudeWave
EN, English
bytedance / MCP Servers · Official registry

UI-TARS-desktop

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

  • 39.4k stars
  • 4k forks
  • 506 open issues
  • Language: TypeScript
  • License: Apache-2.0
  • updated

Install

local · npx
Claude Code CLI
claude mcp add ui-tars-desktop -- npx -y @agent-tars/cli
  1. Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
  2. Replace any <placeholder> values with your API keys or paths.
  3. Restart Claude. The MCP server and its tools appear automatically.

Editor's note

This repository from ByteDance ships two related projects under the TARS umbrella: Agent TARS and UI-TARS Desktop. Agent TARS is a multimodal AI agent accessible via a CLI (`@agent-tars/cli`) and a Web UI, combining GUI automation and vision capabilities with MCP tool integration to handle browser, terminal, and computer tasks. It supports an isolated sandbox execution environment introduced in v0.3.0, along with streaming tool output, timing statistics, and an Event Stream Viewer for debugging. UI-TARS Desktop is a native desktop application built around ByteDance's own UI-TARS vision-language model, offering both local and remote operators for controlling computers and browsers without additional configuration. The stack connects to multimodal LLMs through its own model infrastructure rather than Claude directly, though it exposes MCP server interfaces that make it usable alongside MCP-compatible clients. Developers building GUI automation agents, researchers exploring computer-use workflows, and teams needing scriptable browser or desktop control are the primary audience.

README

MCP Servers overview

Full README on GitHub

Introduction

English | 简体中文

TARS* is a Multimodal AI Agent stack, currently shipping two projects: Agent TARS and UI-TARS-desktop:

Agent TARS UI-TARS-desktop Agent TARS is a general multimodal AI Agent stack, it brings the power of GUI Agent and Vision into your terminal, computer, browser and product. It primarily ships with a CLI and Web UI for usage. It aims to provide a workflow that is closer to human-like task completion through cutting-edge multimodal LLMs and seamless integration with various real-world MCP tools. UI-TARS Desktop is a desktop application that provides a native GUI Agent based on the UI-TARS model. It primarily ships a local and remote computer as well as browser operators.

Table of Contents

News

  • [2025-11-05] 🎉 We're excited to announce the release of Agent TARS CLI v0.3.0! This version brings streaming support for multiple tools (shell commands, multi-file structured display), runtime settings with timing statistics for tool calls and deep thinking, Event Stream Viewer for data flow tracking and debugging. Additionally, it features exclusive support for AIO agent Sandbox as isolated all-in-one tools execution environment.

  • [2025-06-25] We released an Agent TARS Beta and Agent TARS CLI - Introducing Agent TARS Beta, a multimodal AI agent that aims to explore a work form that is closer to human-like task completion through rich multimodal capabilities (such as GUI Agent, Vision) and seamless integration with various real-world tools.

  • [2025-06-12] - 🎁 We are thrilled to announce the release of UI-TARS Desktop v0.2.0! This update introduces two powerful new features: Remote Computer Operator and Remote Browser Operator—both completely free. No configuration required: simply click to remotely control any computer or browser, and experience a new level of convenience and intelligence.

  • [2025-04-17] - 🎉 We're thrilled to announce the release of new UI-TARS Desktop application v0.1.0, featuring a redesigned Agent UI. The application enhances the computer using experience, introduces new browser operation features, and supports the advanced UI-TARS-1.5 model for improved performance and precise control.

  • [2025-02-20] - 📦 Introduced UI TARS SDK, is a powerful cross-platform toolkit for building GUI automation agents.

  • [2025-01-23] - 🚀 We updated the Cloud Deployment section in the 中文版: GUI模型部署教程 with new information related to the ModelScope platform. You can now use the ModelScope platform for deployment.

Agent TARS

Agent TARS is a general multimodal AI Agent stack, it brings the power of GUI Agent and Vision into your terminal, computer, browser and product. It primarily ships with a CLI and Web UI for usage. It aims to provide a workflow that is closer to human-like task completion through cutting-edge multimodal LLMs and seamless integration with various real-world MCP tools.

Showcase

Please help me book the earliest flight from San Jose to New York on September 1st and the last return flight on September 6th on Priceline

https://github.com/user-attachments/assets/772b0eef-aef7-4ab9-8cb0-9611820539d8

Booking Hotel Generate Chart with extra MCP Servers Instruction: I am in Los Angeles from September 1st to September 6th, with a budget of $5,000. Please help me book a Ritz-Carlton hotel closest to the airport on booking.com and compile a transportation guide for me Instruction: Draw me a chart of Hangzhou's weather for one month

For more use cases, please check out #842.

Core Features

  • 🖱️ One-Click Out-of-the-box CLI - Supports both headful Web UI and headless server execution.

  • 🌐 Hybrid Browser Agent - Control browsers using GUI Agent, DOM, or a hybrid strategy.

  • 🔄 Event Stream - Protocol-driven Event Stream drives Context Engineering and Agent UI.

  • 🧰 MCP Integration - The kernel is built on MCP and also supports mounting MCP Servers to connect to real-world tools.

Quick Start

# Launch with `npx`.
npx @agent-tars/cli@latest

# Install globally, required Node.js >= 22
npm install @agent-tars/cli@latest -g

# Run with your preferred model provider
agent-tars --provider volcengine --model doubao-1-5-thinking-vision-pro-250428 --apiKey your-api-key
agent-tars --provider anthropic --model claude-3-7-sonnet-latest --apiKey your-api-key
Topics
agentagent-tarsbrowser-usecomputer-usecoworkgui-agentgui-operatormcpmcp-servermultimodaltarsui-tarsvisionvlm
Frequently asked

What people ask about UI-TARS-desktop

What is bytedance/UI-TARS-desktop?

bytedance/UI-TARS-desktop is mcp servers for the Claude AI ecosystem. The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra It has 39.4k GitHub stars and its last recorded update is dated 2026-10-09.

How do I install UI-TARS-desktop?

You can install UI-TARS-desktop by cloning the repository (https://github.com/bytedance/UI-TARS-desktop) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is bytedance/UI-TARS-desktop safe to use?

Our security agent has analyzed bytedance/UI-TARS-desktop and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains bytedance/UI-TARS-desktop?

bytedance/UI-TARS-desktop is maintained by bytedance. The last recorded GitHub activity is dated 2026-10-09, with 506 open issues.

Are there alternatives to UI-TARS-desktop?

Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.

Maintain this repo? Show its Trust Score in your README

The badge shows this repository's current Trust Score and verdict, and links back to this page. It follows the catalogue data: nobody can buy or edit the score it displays.

ClaudeWave Trust Score for bytedance/UI-TARS-desktop
Markdown (README)
[![ClaudeWave Trust Score for bytedance/UI-TARS-desktop](https://claudewave.com/api/badge/bytedance-ui-tars-desktop)](https://claudewave.com/en/repo/bytedance-ui-tars-desktop)
HTML
<a href="https://claudewave.com/en/repo/bytedance-ui-tars-desktop"><img src="https://claudewave.com/api/badge/bytedance-ui-tars-desktop" alt="ClaudeWave Trust Score for bytedance/UI-TARS-desktop" width="320" height="64"></a>

What the badge means and how the score is computed

Alternatives

See all
Project homepage
https://agent-tars.com