@GitTrend0x: 100% 本地桌面AI Agent 杀手级开源神器 https://github.com/bytedance/UI-TARS-desktop… 这就是 UI-TARS-desktop,字节跳动开源的 31k 星爆款多模态桌面自动化代理! …
摘要
UI-TARS-desktop is a highly popular open-source tool by ByteDance that enables 100% local multimodal desktop automation, allowing users to control apps and browsers via natural language without cloud data leaks.
查看缓存全文
缓存时间: 2026/05/09 16:09
100% 本地桌面AI Agent 杀手级开源神器 https://github.com/bytedance/UI-TARS-desktop… 这就是 UI-TARS-desktop,字节跳动开源的 31k 星爆款多模态桌面自动化代理! 一句话总结:它能看懂你的整个屏幕,用自然语言指挥鼠标键盘,帮你操作任何桌面App和浏览器,全程 100% 本地运行,隐私安全拉满,再也不用把屏幕内容丢给云端! 核心黑科技: • UI-TARS + Seed-1.5-VL 视觉语言模型实时截图理解 • 精准鼠标/键盘控制 + 实时反馈 • 自然语言指令直接搞定一切:打开 VS Code、改系统设置、刷 GitHub、浏览器全自动操作…… • 支持 Windows / macOS / Browser 跨平台 完全开源(Apache 2.0),本地跑模型,无云端、无 API 费用、无数据泄露风险。商业电脑使用代理(Anthropic Computer Use 之流)动辄几百刀/月 + 隐私隐患,这里直接白嫖本地版! 程序员、办公党、重度电脑用户、自动化爱好者的终极解放神器,几分钟部署就能把重复劳动全扔给它干! 再也不用手动点点点了 用了就回不去了
bytedance/UI-TARS-desktop
Source: https://github.com/bytedance/UI-TARS-desktop
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
Visit the comprehensive Quick Start guide for detailed setup instructions.
Documentation
🌟 Explore Agent TARS Universe 🌟
UI-TARS Desktop
UI-TARS Desktop is a native GUI agent for your local computer, driven by UI-TARS and Seed-1.5-VL/1.6 series models.
   📑 Paper   
| 🤗 Hugging Face Models  
|   🫨 Discord  
|   🤖 ModelScope  
🖥️ Desktop Application   
|    👓 Midscene (use in browser)   
Showcase
| Instruction | Local Operator | Remote Operator |
|---|---|---|
| Please help me open the autosave feature of VS Code and delay AutoSave operations for 500 milliseconds in the VS Code setting. | ||
| Could you help me check the latest open issue of the UI-TARS-Desktop project on GitHub? |
Features
- 🤖 Natural language control powered by Vision-Language Model
- 🖥️ Screenshot and visual recognition support
- 🎯 Precise mouse and keyboard control
- 💻 Cross-platform support (Windows/MacOS/Browser)
- 🔄 Real-time feedback and status display
- 🔐 Private and secure - fully local processing
Quick Start
See Quick Start
Contributing
See CONTRIBUTING.md.
License
This project is licensed under the Apache License 2.0.
Citation
If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:
@article{qin2025ui,
title={UI-TARS: Pioneering Automated GUI Interaction with Native Agents},
author={Qin, Yujia and Ye, Yining and Fang, Junjie and Wang, Haoming and Liang, Shihao and Tian, Shizuo and Zhang, Junda and Li, Jiahao and Li, Yunxin and Huang, Shijue and others},
journal={arXiv preprint arXiv:2501.12326},
year={2025}
}
相似文章
@VincentLogic: 发现个字节开源的桌面 AI 神器! UI-TARS Desktop,31k stars 不是吹的,这玩意儿真能看懂你的屏幕,然后帮你自动操作电脑。 你告诉它"帮我把 VS Code 的自动保存打开,延迟改成 500 毫秒",它就自己: -…
字节跳动开源的桌面 AI 自动化工具 UI-TARS Desktop 支持本地运行与屏幕视觉理解,可通过自然语言指令自主操控电脑完成日常任务。
@billtheinvestor: 字节跳动开源 UI-TARS Desktop (3.6k)。核心逻辑:100%本地运行、仅看像素、不调API。对比OpenAI/Anthropic云端模式,解决两大痛点:1. 数据隐私(不出机器);2. 零成本延迟(免API费)。构建私密…
字节跳动开源 UI-TARS Desktop,一款100%本地运行、仅基于像素操作且不调用API的桌面自动化工具,解决数据隐私和API费用两大痛点,为构建私密自动化工作流提供了高效开源方案。
@GoSailGlobal: 字节悄悄把 GUI Agent 这条路线开源了,而且做得比想象中扎实 UI-TARS-desktop(GitHub 29.4k )一个仓库里塞了两个东西: · Agent TARS:通用多模态 Agent 框架,CLI 一键启动,能在终端…
字节跳动开源了 UI-TARS-desktop 项目,包含通用多模态 Agent 框架 Agent TARS 和本地 GUI Agent UI-TARS Desktop,支持在终端/浏览器执行真实任务,基于 UI-TARS 视觉模型和 Seed-1.5-VL,采用 Apache 2.0 许可。
@berryxia: 兄弟们! 不要重复造轮子,直接拿这个31.4K Star的开源来干吧! 字节跳动把 UI-TARS-desktop 开源了,看了一眼,这个项目已经上线快一年了! 目前 Star 数已经来到 31.4k,而且增长速度还挺稳。 24 小时增长…
ByteDance open-sourced UI-TARS-desktop, a native desktop GUI agent with 31.4k GitHub stars that uses vision models to control local or remote applications via natural language. The tool runs locally for privacy, supports Windows and macOS, and includes a CLI with streaming output for developers.
bytedance/UI-TARS-desktop
ByteDance 发布了 TARS,这是一个多模态 AI 智能体技术栈,包含 Agent TARS(基于 CLI/Web UI 的通用 AI 智能体,支持 GUI、浏览器和终端任务)和 UI-TARS Desktop(由 UI-TARS 模型驱动的原生桌面应用,用于本地和远程计算机/浏览器自动化)。该技术栈将多模态 LLM 与 MCP 工具相结合,实现类人任务处理能力。