UI-TARS-desktop

Overview

This project is a multimodal AI agent stack comprising Agent TARS (CLI/Web UI) and UI-TARS Desktop. It enables GUI agent, browser, and computer operations, integrating with MCP tools for human-like task automation.

README Preview

\n  \n\n\n\n\n## Introduction\n\nEnglish | [简体中文](./README.zh-CN.md)\n\n[](https://trendshift.io/repositories/13584)\n\nTARS\* is a Multimodal AI Agent stack, currently shipping two projects: [Agent TARS](#agent-tars) and [UI-TARS-desktop](#ui-tars-desktop):\n\n\n  \n    \n      Agent TARS\n      UI-TARS-desktop\n    \n  \n  \n    \n      \n        \n      \n      \n        \n      \n    \n    \n      \n        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.\n        \n        \n        It primarily ships with a CLI and Web UI for usage.\n        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.\n      \n      \n        UI-TARS Desktop is a desktop application that provides a native GUI Agent based on the UI-TARS model.\n        \n        \n        It primarily ships a\n        local and \n        remote computer as well as browser operators.\n      \n    \n  \n\n\n## Table of Contents\n\n\n\n\n- [News](#news)\n- [Agent TARS](#agent-tars)\n  - [Showcase](#showcase)\n  - [Core Features](#core-features)\n  - [Quick Start](#quick-start)\n  - [Documentation](#documentation)\n- [UI-TARS Desktop](#ui-tars-desktop)\n  - [Showcase](#showcase-1)\n  - [Features](#features)\n  - [Quick Start](#quick-start-1)\n- [Contributing](#contributing)\n- [License](#license)\n- [Citation](#citation)\n\n\n\n## News\n\n- **\[2025-11-05\]** 🎉 We're excited to announce the release of [Agent TARS CLI v0.3.0](https://github.com/bytedance/UI-TARS-desktop/releases/tag/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](ht

FAQ (1)