UI-TARS Desktop
- desktop-chat
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
About
What is UI-TARS Desktop?
UI-TARS Desktop is a GUI Agent application based on the UI-TARS Vision-Language Model that lets you control your computer using natural language. It runs on Windows, macOS, and browser environments and is designed for users who want to automate graphical user interface tasks through language commands.
How to use UI-TARS Desktop?
Refer to the Quick Start guide and Deployment documentation provided in the repository for setup instructions. The application processes input locally to ensure privacy and security.
Key features of UI-TARS Desktop
- Natural language control powered by a 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
Use cases of UI-TARS Desktop
- Open VS Code settings and configure autosave parameters via natural language
- Check the latest open issue on a GitHub project
- Perform any GUI-based computer task by describing it in plain language
FAQ from UI-TARS Desktop
What is UI-TARS Desktop and how does it differ from other GUI automation tools?
UI-TARS Desktop is a desktop application that interprets natural language to control the computer through visual recognition and direct mouse/keyboard actions, leveraging the UI-TARS vision-language model for enhanced accuracy.
Which platforms and models are supported?
The application supports Windows, macOS, and browser environments. It incorporates the UI-TARS-1.5 model for improved performance and precise control.
Does UI-TARS Desktop support custom MCP servers?
The README does not mention MCP server support.
Is UI-TARS Desktop free and what is its license?
The application is licensed under Apache License 2.0; no pricing information is provided in the README.
Are there any known limitations or restrictions?
The README does not list specific limitations, but notes that the application is in a technical preview stage and focuses on local processing for privacy.
Details
- Author
- bytedance
- GitHub stars
- 14,476
- Category
- desktop-chat
- Repository
- bytedance/ui-tars-desktop
> [!IMPORTANT]
> <a href="./apps/agent-tars/README.md">
> <img src="./apps/agent-tars/static/hero.png">
> </a>
>
> \[2025-03-18\] We released a technical preview version of a new desktop app - Agent TARS, a multimodal AI agent that leverages browser operations by visually interpreting web pages and seamlessly integrating with command lines and file systems.
<p align="center">
<img alt="UI-TARS" width="260" src="./apps/ui-tars/resources/icon.png">
</p>
UI-TARS Desktop
UI-TARS Desktop is a GUI Agent application based on UI-TARS (Vision-Language Model) that allows you to control your computer using natural language.
<div align="center">
<p>
   📑 <a href="https://arxiv.org/abs/2501.12326">Paper</a>   
| 🤗 <a href="https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B">Hugging Face Models</a>  
|   🫨 <a href="https://discord.gg/pTXwYVjfcs">Discord</a>  
|   🤖 <a href="https://www.modelscope.cn/collections/UI-TARS-bccb56fa1ef640">ModelScope</a>  
<br>
🖥️ Desktop Application   
|    👓 <a href="https://github.com/web-infra-dev/midscene">Midscene (use in browser)</a>   
|    <a href="https://deepwiki.com/bytedance/UI-TARS-desktop">
<img alt="Ask DeepWiki.com" src="https://devin.ai/assets/deepwiki-badge.png" style="height: 18px; vertical-align: middle;">
</a>
</p>
</div>
Showcases
| Instruction | Video |
| :---: | :---: |
| Please help me open the autosave feature of VS Code and delay AutoSave operations for 500 milliseconds in the VS Code setting. | <video src="https://github.com/user-attachments/assets/e0914ce9-ad33-494b-bdec-0c25c1b01a27" height="300" /> |
| Could you help me check the latest open issue of the UI-TARS-Desktop project on GitHub? | <video src="https://github.com/user-attachments/assets/3d159f54-d24a-4268-96c0-e149607e9199" height="300" /> |
News
- \[2025-04-17\] - 🎉 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.
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.
Deployment
See Deployment.
Contributing
See CONTRIBUTING.md.
SDK (Experimental)
See @ui-tars/sdk
License
UI-TARS Desktop 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}
}

