UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
claude mcp add --transport stdio bytedance-ui-tars-desktop node path/to/server.js
How to use
UI-TARS Desktop is a desktop application that provides a native GUI Agent based on the UI-TARS model. It allows users to operate both local and remote computers and browsers seamlessly. Users can initiate operations by selecting either the local or remote options, which enables them to control their devices or browsers without any complex configurations. The application aims to enhance productivity and user experience by leveraging advanced multimodal AI capabilities.
How to install
To install UI-TARS Desktop, ensure you have Node.js installed on your machine. First, clone the repository using the command:
git clone https://github.com/bytedance/UI-TARS-desktop.git
Next, navigate into the cloned directory:
cd UI-TARS-desktop
Then, install the necessary dependencies:
npm install
Finally, start the application with:
node path/to/server.js
Additional notes
Make sure to check the compatibility of your Node.js version with the application. If you encounter issues during installation, ensure all dependencies are correctly installed and that you have the necessary permissions to run the application. Environment variables may be required for specific functionalities, so refer to the documentation for any additional configuration options.
Related MCP Servers
TuriX-CUA
This is the official website for TuriX Computer-use-Agent
multimodal-agents-course
An MCP Multimodal AI Agent with eyes and ears!
sonarqube
SonarQube MCP Server
skillz
An MCP server for loading skills (shim for non-claude clients).
evm
MCP server that provides LLMs with tools for interacting with EVM networks
mem0
✨ mem0 MCP Server: A memory system using mem0 for AI applications with model context protocl (MCP) integration. Enables long-term memory for AI agents as a drop-in MCP server.