The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
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. |
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.
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 Pricelinehttps://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.
# 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-keyVisit the comprehensive Quick Start guide for detailed setup instructions.
🌟 Explore Agent TARS Universe 🌟
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.
| 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? | <video src="https |
[Bug Report]: 拉完了！简直Token粉碎机！
[Bug Report]: filesystem move_file overwrites existing destination files despite its no-overwrite contract
docs(tarko): agent README documents maxIterations default as 10, code ships 1000
XMLFormatParser coerces numeric XML tag values, silently dropping action inputs
docs(sdk): maxLoopCount default is documented as 25 but the code default is MAX_LOOP_COUNT = 100
GUIAgent: a paused run loop cannot be released by stop(), by the documented abort signal, or (after a second pause()) by resume()
model-provider: a configured `anthropic_beta` list in `model.params` is replaced instead of merged for Azure Claude models
ImageProcessor logs hard-coded format: 'webp' and quality: 80 in its compression stats instead of the configured options
model-provider: a configured `anthropic-beta` header is replaced instead of merged, so no Claude beta flag can be requested
ConsoleInterceptor's JSON.stringify renderer erases Error arguments and throws inside the wrapped run