中文 | English

HyperChat is an open Chat client that can utilize APIs from various LLMs, fully supporting MCP for the best Chat experience. It also implements productivity MAX tools based on native Agents.

• Supports OpenAI-style LLMs, OpenAI, Claude(OpenRouter), Qwen, Deepseek, GLM, Ollama.
• Built-in MCP plugin market with user-friendly MCP installation and configuration, one-click installation, and welcome submissions for HyperChatMCP.
• Also supports manual installation of third-party MCPs, just fill in command, args, and env.

• HyperChat on Docker

• 🪟Windows + 🍏MacOS + Linux
• Run from the command line, npx -y @dadigua/hyper-chat, default port 16100, password 123456, web access http://localhost:16100/123456/
• Docker
  • Command line version docker pull dadigua/hyperchat-mini:latest
  • Ubuntu desktop + Chrome + BrowserUse version (coming soon)
• MCP extension market + third-party MCP support
• Supports free creation and design of Agent, with preset prompts and selection of MCP features
• Supports dark mode🌙
• Supports Resources, Prompts, and Tools
• Supports English and Chinese
• Supports Artifacts, SVG, HTML rendering, JavaScript error capturing, and opening Chrome's console
• Agent display optimization, supports searching and drag-and-drop sorting
• Supports KaTeX, displaying mathematical formulas, code rendering with highlighting and quick copy
• WebDAV synchronization
• Added RAG, based on MCP knowledge base
• Introduced ChatSpace concept, supports multiple conversations simultaneously
• Supports Agent Call Agent through HyperAgent's MCP
• Added scheduled tasks, specify Agent to complete tasks at specified times and view task completion status.

• A Docker version will be added later, with a built-in Linux desktop, built-in Chrome configured remote port, unified environment for better usability. Then a web interface control. Usable on any device, including mobile🤣
• Permission pop-up, whether to allow
• Implement LLM writing MCP for itself

• 1. Configure APIKEY, ensure your LLM service is compatible with OpenAI style.
• 1. Ensure uv + nodejs is installed in your system.

Install via command line or check the official GitHub tutorial uv

# MacOS
brew install uv
# Windows
winget install --id=astral-sh.uv  -e

Install via command line or download from the official site, nodejs

# MacOS
brew install node
# Windows
winget install OpenJS.NodeJS.LTS

cd electron && npm install
cd web && pnpm install
npm install
npm run dev

• On MacOS, if you encounter issues with it being damaged or permissions, run sudo xattr -d com.apple.quarantine /Applications/HyperChat.app
• MacOS nvm users manually input PATH echo $PATH, Windows version nvm seems to work directly

HyperChat User Community

• This project is for educational and communication purposes only. If you use this project for any operation, such as web scraping, it has no connection with the developers of this project.