{ "markdown": "\n \"Agent\n\n\n
\n\n## Introduction\n\nEnglish | [็ฎ€ไฝ“ไธญๆ–‡](./README.zh-CN.md)\n\n[![](https://trendshift.io/api/badge/repositories/13584)](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 \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Agent TARSUI-TARS-desktop
\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 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## 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\\]** ๐ŸŽ‰ 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.\n- **\\[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.\n- **\\[2025-06-12\\]** - ๐ŸŽ 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**โ€”both completely free. No configuration required: simply click to remotely control any computer or browser, and experience a new level of convenience and intelligence.\n- **\\[2025-04-17\\]** - ๐ŸŽ‰ 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.\n- **\\[2025-02-20\\]** - ๐Ÿ“ฆ Introduced [UI TARS SDK](./docs/sdk.md), is a powerful cross-platform toolkit for building GUI automation agents.\n- **\\[2025-01-23\\]** - ๐Ÿš€ We updated the **[Cloud Deployment](./docs/deployment.md#cloud-deployment)** section in the ไธญๆ–‡็‰ˆ: [GUIๆจกๅž‹้ƒจ็ฝฒๆ•™็จ‹](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.\n\n
\n\n## Agent TARS\n\n

\n \"npm\n \"downloads\"\n \"node\n \"Discord\n \"Official\n \"้ฃžไนฆไบคๆต็พค\"\n \"Ask\n

\n\nAgent TARS is a general multimodal AI Agent stack, it brings the power of GUI Agent and Vision into your terminal, computer, browser and product.

\nIt primarily ships with a CLI and Web UI for usage.\nIt 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### Showcase\n\n```\nPlease 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\n```\n\nhttps://github.com/user-attachments/assets/772b0eef-aef7-4ab9-8cb0-9611820539d8\n\n
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Booking HotelGenerate Chart with extra MCP Servers
\n \n \n \n
\n 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\n \n Instruction: Draw me a chart of Hangzhou's weather for one month\n
\n\nFor more use cases, please check out [#842](https://github.com/bytedance/UI-TARS-desktop/issues/842).\n\n### Core Features\n\n- ๐Ÿ–ฑ๏ธ **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).\n- ๐ŸŒ **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.\n- ๐Ÿ”„ **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).\n- ๐Ÿงฐ **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.\n\n### Quick Start\n\n\"Agent\n\n```bash\n# Launch with `npx`.\nnpx @agent-tars/cli@latest\n\n# Install globally, required Node.js >= 22\nnpm install @agent-tars/cli@latest -g\n\n# Run with your preferred model provider\nagent-tars --provider volcengine --model doubao-1-5-thinking-vision-pro-250428 --apiKey your-api-key\nagent-tars --provider anthropic --model claude-3-7-sonnet-latest --apiKey your-api-key\n```\n\nVisit the comprehensive [Quick Start](https://agent-tars.com/guide/get-started/quick-start.html) guide for detailed setup instructions.\n\n### Documentation\n\n> ๐ŸŒŸ **Explore Agent TARS Universe** ๐ŸŒŸ\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
CategoryResource LinkDescription
๐Ÿ  Central Hub\n \n \"Website\"\n \n Your gateway to Agent TARS ecosystem
๐Ÿ“š Quick Start\n \n \"Quick\n \n Zero to hero in 5 minutes
๐Ÿš€ What's New\n \n \"Blog\"\n \n Discover cutting-edge features & vision
๐Ÿ› ๏ธ Developer Zone\n \n \"Docs\"\n \n Master every command & features
๐ŸŽฏ Showcase\n \n \"Examples\"\n \n View use cases built by the official and community
๐Ÿ”ง Reference\n \n \"API\"\n \n Complete technical reference
\n\n
\n
\n
\n\n## UI-TARS Desktop\n\n

\n \"UI-TARS\"\n

\n\nUI-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.\n\n
\n

\n    ๐Ÿ“‘ Paper   \n | ๐Ÿค— Hugging Face Models  \n |   ๐Ÿซจ Discord  \n |   ๐Ÿค– ModelScope  \n
\n๐Ÿ–ฅ๏ธ Desktop Application   \n|    ๐Ÿ‘“ Midscene (use in browser)   \n

\n\n
\n\n### Showcase\n\n\n\n| Instruction | Local Operator | Remote Operator |\n| :----------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------: |\n| Please help me open the autosave feature of VS Code and delay AutoSave operations for 500 milliseconds in the VS Code setting. |