## File: README.md

## Introduction

English | [简体中文](./README.zh-CN.md)

[](https://trendshift.io/repositories/13584)

**TARS<sup>\*</sup>** is a Multimodal AI Agent stack, currently shipping two projects: [Agent TARS](#agent-tars) and [UI-TARS-desktop](#ui-tars-desktop):



| [Agent TARS](#agent-tars) | [UI-TARS-desktop](#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](https://agent-tars.com/guide/basic/cli.html) and [Web UI](https://agent-tars.com/guide/basic/web-ui.html) 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](https://agent-tars.com/guide/basic/mcp.html) tools. | **UI-TARS Desktop** is a desktop application that provides a native GUI Agent based on the [UI-TARS](https://github.com/bytedance/UI-TARS) model.
        
        
        It primarily ships a
        [local](https://github.com/bytedance/UI-TARS-desktop/blob/main/docs/quick-start.md#get-model-and-run-local-operator) and 
        [remote](https://github.com/bytedance/UI-TARS-desktop/blob/main/docs/quick-start.md#run-remote-operator) computer as well as browser operators. |



## Table of Contents




- [News](#news)
- [Agent TARS](#agent-tars)
  - [Showcase](#showcase)
  - [Core Features](#core-features)
  - [Quick Start](#quick-start)
  - [Documentation](#documentation)
- [UI-TARS Desktop](#ui-tars-desktop)
  - [Showcase](#showcase-1)
  - [Features](#features)
  - [Quick Start](#quick-start-1)
- [Contributing](#contributing)
- [License](#license)
- [Citation](#citation)



## News

- **\[2025-11-05\]** 🎉 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](https://github.com/agent-infra/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](https://agent-tars.com/blog/2025-06-25-introducing-agent-tars-beta.html), 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](https://seed-tars.com/1.5) for improved performance and precise control.
- **\[2025-02-20\]** - 📦 Introduced [UI TARS SDK](./docs/sdk.md), is a powerful cross-platform toolkit for building GUI automation agents.
- **\[2025-01-23\]** - 🚀 We updated the **[Cloud Deployment](./docs/deployment.md#cloud-deployment)** section in the 中文版: [GUI模型部署教程](https://bytedance.sg.larkoffice.com/docx/TCcudYwyIox5vyxiSDLlgIsTgWf#U94rdCxzBoJMLex38NPlHL21gNb) with new information related to the ModelScope platform. You can now use the ModelScope platform for deployment.



## Agent TARS


    [](https://npmjs.com/package/@agent-tars/cli?activeTab=readme)
    [](https://npmcharts.com/compare/@agent-tars/cli?minimal=true)
    [](https://nodejs.org/en/about/previous-releases)
    [](https://discord.gg/HnKcSBgTVx)
    [](https://twitter.com/agent_tars)
    [](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=deen76f4-ea3c-4964-93a3-78f126f39651)
    [](https://deepwiki.com/bytedance/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](https://agent-tars.com/guide/basic/cli.html) and [Web UI](https://agent-tars.com/guide/basic/web-ui.html) 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](https://agent-tars.com/guide/basic/mcp.html) 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](https://github.com/bytedance/UI-TARS-desktop/issues/842).

### Core Features

- 🖱️ **One-Click Out-of-the-box CLI** - Supports both **headful** [Web UI](https://agent-tars.com/guide/basic/web-ui.html) and **headless** [server](https://agent-tars.com/guide/advanced/server.html) [execution](https://agent-tars.com/guide/basic/cli.html).
- 🌐 **Hybrid Browser Agent** - Control browsers using [GUI Agent](https://agent-tars.com/guide/basic/browser.html#visual-grounding), [DOM](https://agent-tars.com/guide/basic/browser.html#dom), or a hybrid strategy.
- 🔄 **Event Stream** - Protocol-driven Event Stream drives [Context Engineering](https://agent-tars.com/beta#context-engineering) and [Agent UI](https://agent-tars.com/blog/2025-06-25-introducing-agent-tars-beta.html#easy-to-build-applications).
- 🧰 **MCP Integration** - The kernel is built on MCP and also supports mounting [MCP Servers](https://agent-tars.com/guide/basic/mcp.html) to connect to real-world tools.

### Quick Start



```bash
# 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](https://agent-tars.com/guide/get-started/quick-start.html) 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](https://github.com/bytedance/UI-TARS) and Seed-1.5-VL/1.6 series models.



### 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. | <video src="https://github.com/user-attachments/assets/e0914ce9-ad33-494b-bdec-0c25c1b01a27" height="300" /> | <video src="https://github.com/user-attachments/assets/01e49b69-7070-46c8-b3e3-2aaaaec71800" 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" /> | <video src="https://github.com/user-attachments/assets/072fb72d-7394-4bfa-95f5-4736e29f7e58" height="300" /> |

### 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](./docs/quick-start.md)

## Contributing

See [CONTRIBUTING.md](./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}
}
```

---

## File: docs/archive-1.0/deployment.md

> [!WARNING]
> This document has been archived.

# Deployment

### ⚠️ Important Announcement: GGUF Model Performance

The **GGUF model** has undergone quantization, but unfortunately, its performance cannot be guaranteed. As a result, we have decided to **downgrade** it.

💡 **Alternative Solution**:
You can use **[Cloud Deployment](#cloud-deployment)** or **[Local Deployment [vLLM]](#local-deployment-vllm)**(If you have enough GPU resources) instead.

We appreciate your understanding and patience as we work to ensure the best possible experience.

## Cloud Deployment

We recommend using HuggingFace Inference Endpoints for fast deployment.
We provide two docs for users to refer:

English version: [GUI Model Deployment Guide](https://juniper-switch-f10.notion.site/GUI-Model-Deployment-Guide-17b5350241e280058e98cea60317de71)

中文版: [GUI模型部署教程](https://bytedance.sg.larkoffice.com/docx/TCcudYwyIox5vyxiSDLlgIsTgWf#U94rdCxzBoJMLex38NPlHL21gNb)

## Local Deployment [vLLM]
We recommend using vLLM for fast deployment and inference. You need to use `vllm>=0.6.1`.
```bash
pip install -U transformers
VLLM_VERSION=0.6.6
CUDA_VERSION=cu124
pip install vllm==${VLLM_VERSION} --extra-index-url https://download.pytorch.org/whl/${CUDA_VERSION}

```
### Download the Model
We provide three model sizes on Hugging Face: **2B**, **7B**, and **72B**. To achieve the best performance, we recommend using the **7B-DPO** or **72B-DPO** model (based on your hardware configuration):

- [2B-SFT](https://huggingface.co/bytedance-research/UI-TARS-2B-SFT)
- [7B-SFT](https://huggingface.co/bytedance-research/UI-TARS-7B-SFT)
- [7B-DPO](https://huggingface.co/bytedance-research/UI-TARS-7B-DPO)
- [72B-SFT](https://huggingface.co/bytedance-research/UI-TARS-72B-SFT)
- [72B-DPO](https://huggingface.co/bytedance-research/UI-TARS-72B-DPO)


### Start an OpenAI API Service
Run the command below to start an OpenAI-compatible API service:

```bash
python -m vllm.entrypoints.openai.api_server --served-model-name ui-tars --model 
```

### Input your API information





> **Note**: VLM Base Url is OpenAI compatible API endpoints (see [OpenAI API protocol document](https://platform.openai.com/docs/guides/vision/uploading-base-64-encoded-images) for more details).

---

## File: docs/archive-1.0/preset.md

> [!WARNING]
> This document has been archived.

# Preset Management Guide

> [!IMPORTANT]  
> Currently, **UI-TARS Desktop** does not directly provide server-side capabilities, so we do not provide a Preset for the open source community. welcome community developers to contribute your presets [here](../examples/presets/).

A **preset** is a collection of [settings](./setting.md)  (_Introduced at [#61](https://github.com/bytedance/UI-TARS-desktop/pull/61)_), **UI-TARS Desktop** supports import presets via `files` or `URLs`:

```mermaid
graph TD
    A[Import Preset] --> B{Preset Type}
    B -->|File| C[YAML File]
    B -->|URL| D[URL Endpoint]
    C --> E[Manual Updates 🔧]
    D --> F[Auto Sync ⚡]
```




## Preset Types Comparison

| Feature               | Local Presets          | Remote Presets         |
|-----------------------|------------------------|------------------------|
| **Storage**           | Device-local           | Cloud-hosted          |
| **Update Mechanism**  | Manual                 | Automatic             |
| **Access Control**    | Read/Write             | Read-Only             |
| **Versioning**        | Manual                 | Git-integrated        |






## Examples

### Import from file

**UI-TARS Desktop** supports importing presets from files. Once the file is parsed successfully, the settings will be automatically updated.

| Function | Snapshot |
| --- | ---|
| Open Setting | |
| Import Success | |
| Exception: Invalid Content |  |





### Import from URL

**UI-TARS Desktop** also supports importing presets from URLs. If automatic updates are set, presets will be automatically pulled every time the application is started.

| Function | Snapshot |
| --- | ---|
| Open Setting |  |
| Import Success (Default) |  |
| Import Success (Auto Update) | |





### Preset Example

```yaml
name: UI TARS Desktop Example Preset
language: en
vlmProvider: Hugging Face
vlmBaseUrl: https://your-endpoint.huggingface.cloud/v1
vlmApiKey: your_api_key
vlmModelName: your_model_name
reportStorageBaseUrl: https://your-report-storage-endpoint.com/upload
utioBaseUrl: https://your-utio-endpoint.com/collect
```

See all [example presets](../examples/presets).

---

## File: docs/archive-1.0/quick-start.md

> [!WARNING]
> This document has been archived.

# Quick Start

## Download

You can download the [latest release](https://github.com/bytedance/UI-TARS-desktop/releases/latest) version of UI-TARS Desktop from our releases page.

> **Note**: If you have [Homebrew](https://brew.sh/) installed, you can install UI-TARS Desktop by running the following command:
> ```bash
> brew install --cask ui-tars
> ```

## Install

### MacOS

1. Drag **UI TARS** application into the **Applications** folder
  

2. Enable the permission of **UI TARS** in MacOS:
  - System Settings -> Privacy & Security -> **Accessibility**
  - System Settings -> Privacy & Security -> **Screen Recording**
  

3. Then open **UI TARS** application, you can see the following interface:
  


### Windows

**Still to run** the application, you can see the following interface:

---

## File: docs/archive-1.0/README.md

# UI-TARS Desktop

UI-TARS Desktop is a GUI Agent application based on [UI-TARS (Vision-Language Model)](https://github.com/bytedance/UI-TARS) that allows you to control your computer using natural language.




## Showcases

| Instruction  | Video |
| :---:  | :---: |
| Get the current weather in SF using the web browser      |    <video src="https://github.com/user-attachments/assets/5235418c-ac61-4895-831d-68c1c749fc87" height="300" />    |
| Send a twitter with the content "hello world"   | <video src="https://github.com/user-attachments/assets/737ccc11-9124-4464-b4be-3514cbced85c" height="300" />        |


## News

- **\[2025-04-17\]** - 🎉 We're excited to announce support for **UI-TARS-1.5**, featuring enhanced performance, precise control, and expanded scenario coverage (using computer and browser as operators). Now compatible with multiple models: UI-TARS-1.0, UI-TARS-1.5, and Doubao-1.5-UI-TARS!
- **\[2025-02-20\]** - 📦 Introduced [UI TARS SDK](./sdk.md), is a powerful cross-platform toolkit for building GUI automation agents.
- **\[2025-01-23\]** - 🚀 We updated the **[Cloud Deployment](./deployment.md#cloud-deployment)** section in the 中文版: [GUI模型部署教程](https://bytedance.sg.larkoffice.com/docx/TCcudYwyIox5vyxiSDLlgIsTgWf#U94rdCxzBoJMLex38NPlHL21gNb) 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)
- 🔄 Real-time feedback and status display
- 🔐 Private and secure - fully local processing

## Quick Start

See [Quick Start](./quick-start.md).

## Deployment

See [Deployment](./deployment.md).

## Contributing

See [CONTRIBUTING.md](./CONTRIBUTING.md).

## SDK (Experimental)

See [@ui-tars/sdk](./sdk.md)

## 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:

```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}
}
```