https://github.com/bytedance/ui-tars-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Science Score: 46.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
✓Committers with academic emails
1 of 30 committers (3.3%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (12.9%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Basic Info
- Host: GitHub
- Owner: bytedance
- License: apache-2.0
- Language: TypeScript
- Default Branch: main
- Homepage: https://agent-tars.com
- Size: 176 MB
Statistics
- Stars: 18,227
- Watchers: 151
- Forks: 1,730
- Open Issues: 295
- Releases: 36
Topics
Metadata Files
README.md
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
- [2025-06-25] We released a 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
```bash
Luanch 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 🌟
| Category | Resource Link | Description |
|---|---|---|
| 🏠 Central Hub |
|
Your gateway to Agent TARS ecosystem |
| 📚 Quick Start |
|
Zero to hero in 5 minutes |
| 🚀 What's New |
|
Discover cutting-edge features & vision |
| 🛠️ Developer Zone |
|
Master every command & features |
| 🎯 Showcase |
|
View use cases built by the official and community |
| 🔧 Reference |
|
Complete technical reference |
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:
BibTeX
@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}
}
Owner
- Name: Bytedance Inc.
- Login: bytedance
- Kind: organization
- Location: Singapore
- Website: https://opensource.bytedance.com
- Twitter: ByteDanceOSS
- Repositories: 255
- Profile: https://github.com/bytedance
Committers
Last synced: 9 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Charles | j****1@b****m | 122 |
| ULIVZ | c****i@b****m | 80 |
| skychx | s****x@h****m | 18 |
| wanghaoming.whm | w****m@b****m | 16 |
| heh | 3****h | 15 |
| yangxingyuan | 3****4 | 9 |
| Willem Jiang | w****g@g****m | 6 |
| ycjcl868 | c****n@g****m | 5 |
| Lynx • 琅邪 | l****a@g****m | 3 |
| duguangyu.d | d****d@b****m | 3 |
| le0zh | n****t@q****m | 3 |
| yc.ai | 7****n | 3 |
| Aaron Young | l****1@g****m | 2 |
| omahs | 7****s | 2 |
| Willem Jiang | 1****d | 2 |
| StepSecurity Bot | b****t@s****o | 2 |
| Eno Cyrus | g****e@g****m | 2 |
| 老果冻 | 4****g | 1 |
| 5101good | 5****d@1****m | 1 |
| Ikko Eltociear Ashimine | e****r@g****m | 1 |
| Prateek Garg | 5****8 | 1 |
| QuietlyChan | q****n@f****m | 1 |
| Sangyun_LEE (이상윤) | f****6@c****r | 1 |
| Shixian Sheng | s****2@p****m | 1 |
| SunShineGo | 5****8 | 1 |
| Yiyao (Jim) Wan | y****n@u****u | 1 |
| fix-echo | l****8@q****m | 1 |
| quicksand | q****n@g****m | 1 |
| yuyutaotao | 1****o | 1 |
| zac_ma | y****g@o****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 5 months ago
All Time
- Total issues: 415
- Total pull requests: 1,283
- Average time to close issues: 3 days
- Average time to close pull requests: about 20 hours
- Total issue authors: 233
- Total pull request authors: 48
- Average comments per issue: 0.76
- Average comments per pull request: 0.94
- Merged pull requests: 975
- Bot issues: 0
- Bot pull requests: 36
Past Year
- Issues: 415
- Pull requests: 1,283
- Average time to close issues: 3 days
- Average time to close pull requests: about 20 hours
- Issue authors: 233
- Pull request authors: 48
- Average comments per issue: 0.76
- Average comments per pull request: 0.94
- Merged pull requests: 975
- Bot issues: 0
- Bot pull requests: 36
Top Authors
Issue Authors
- ulivz (136)
- jjy1000 (5)
- PepperPlatypus (4)
- ycjcl868 (4)
- gitboy123 (4)
- youngjuning (3)
- zhuzeyu22 (3)
- wisepmlin (3)
- zz6zz666 (3)
- asunoiwin (3)
- NiksaSprinting (2)
- OlafStolle (2)
- skychx (2)
- SimFG (2)
- MurphyYe (2)
Pull Request Authors
- ulivz (676)
- ycjcl868 (272)
- ZhaoHeh (89)
- skychx (60)
- dependabot[bot] (36)
- cjraft (21)
- WillemJiang (14)
- sanyuan0704 (14)
- le0zh (10)
- youngjuning (6)
- lynxlangya (6)
- helio9cn (6)
- knoxnoe (4)
- omahs (4)
- step-security-bot (4)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 24
-
Total downloads:
- npm 463,478 last-month
-
Total dependent packages: 0
(may contain duplicates) -
Total dependent repositories: 0
(may contain duplicates) - Total versions: 648
- Total maintainers: 6
proxy.golang.org: github.com/bytedance/ui-tars-desktop
- Documentation: https://pkg.go.dev/github.com/bytedance/ui-tars-desktop#section-documentation
- License: apache-2.0
-
Latest release: v0.2.4
published 6 months ago
Rankings
proxy.golang.org: github.com/bytedance/UI-TARS-desktop
- Documentation: https://pkg.go.dev/github.com/bytedance/UI-TARS-desktop#section-documentation
- License: apache-2.0
-
Latest release: v0.2.4
published 6 months ago
Rankings
npmjs.org: @gui-agent/operator-aio
AIO (All-in-One) operator for GUI Agent
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 0.3.0-beta.11
published 5 months ago
Rankings
Maintainers (1)
npmjs.org: @ui-tars/operator-adb
Operator Android SDK for UI-TARS
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 1.2.3
published 8 months ago
Rankings
npmjs.org: @gui-agent/operator-browser
Native-browser operator for GUI Agent
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 0.3.0-beta.11
published 5 months ago
Rankings
Maintainers (1)
npmjs.org: @ui-tars/operator-browser
Native-browser operator for UI-TARS
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 1.2.3
published 8 months ago
Rankings
npmjs.org: @agent-infra/mcp-server-commands
An MCP server to run arbitrary commands
- Homepage: https://github.com/bytedance/UI-TARS-desktop
- License: apache-2.0
-
Latest release: 1.2.22
published 5 months ago
Rankings
Maintainers (5)
npmjs.org: @gui-agent/action-parser
Action parser SDK for general action parser
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 0.3.0-beta.11
published 5 months ago
Rankings
Maintainers (1)
npmjs.org: @hivelogic/mcp-server-browser
MCP server for browser use access
- Homepage: https://github.com/bytedance/UI-TARS-desktop
- License: MIT
-
Latest release: 1.2.16
published 7 months ago
Rankings
Maintainers (1)
npmjs.org: create-new-mcp
Create MCP server template
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: MIT
-
Latest release: 1.1.3
published 5 months ago
Rankings
Maintainers (1)
npmjs.org: @agent-infra/mcp-http-server
High performance HTTP Server for MCP
- Homepage: https://github.com/bytedance/UI-TARS-desktop
- License: MIT
-
Latest release: 1.1.1-beta.2
published 9 months ago
Rankings
Maintainers (5)
npmjs.org: mcp-http-server
High performance HTTP Server for MCP
- Homepage: https://github.com/bytedance/UI-TARS-desktop
- License: MIT
-
Latest release: 1.2.4
published 7 months ago
Rankings
Maintainers (1)
npmjs.org: @agent-infra/mcp-shared
MCP shared
- Homepage: https://github.com/bytedance/UI-TARS-desktop
- License: MIT
-
Latest release: 1.2.22
published 5 months ago
Rankings
Maintainers (5)
npmjs.org: @agent-infra/mcp-server-filesystem
MCP server for filesystem access
- Homepage: https://github.com/bytedance/UI-TARS-desktop
- License: MIT
-
Latest release: 1.2.22
published 5 months ago
Rankings
Maintainers (5)
npmjs.org: @agent-infra/mcp-client
An MCP Client to run servers for Electron apps, support same-process approaching
- Homepage: https://github.com/bytedance/UI-TARS-desktop
- License: apache-2.0
-
Latest release: 1.2.22
published 5 months ago
Rankings
Maintainers (5)
npmjs.org: @agent-infra/mcp-server-browser
MCP server for browser use access
- Homepage: https://github.com/bytedance/UI-TARS-desktop
- License: MIT
-
Latest release: 1.2.22
published 5 months ago
Rankings
Maintainers (5)
npmjs.org: @ui-tars/operator-browserbase
Operator Browserbase SDK for UI-TARS
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 1.2.3
published 8 months ago
Rankings
npmjs.org: @ui-tars/operator-nut-js
Operator Nut JS SDK for UI-TARS
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 1.2.3
published 8 months ago
Rankings
npmjs.org: @ui-tars/cli
CLI for UI-TARS
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 1.2.3
published 8 months ago
Rankings
npmjs.org: @ui-tars/electron-ipc
Type-safe Electron inter-process communication for UI-TARS
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 1.2.3
published 12 months ago
Rankings
npmjs.org: @ui-tars/sdk
A powerful cross-platform(ANY device/platform) toolkit for building GUI automation agents for UI-TARS
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 1.2.3
published 8 months ago
Rankings
npmjs.org: @ui-tars/visualizer
Visualizer for Computer Use forked from @midscene/visualizer
- Homepage: https://github.com/bytedance/UI-TARS-desktop/tree/main/packages/visualizer
- License: apache-2.0
-
Latest release: 1.1.0
published about 1 year ago
Rankings
npmjs.org: @ui-tars/shared
Shared types for UI-TARS
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 1.2.3
published 8 months ago
Rankings
npmjs.org: @ui-tars/action-parser
Action parser SDK for UI-TARS
- Homepage: https://github.com/bytedance/UI-TARS-desktop#readme
- License: Apache-2.0
-
Latest release: 1.2.3
published 8 months ago