HyperChat

中文 | English

Introduction

HyperChat is an open pursuit Chat client that can use APIs from various LLMs, fully supporting MCP to achieve the best chat experience, as well as a production MAX tool based on native Agents.

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

DEMO

• HyperChat on Docker

Features:

• 🪟Windows + 🍏MacOS + Linux
• Command line execution, npx -y @dadigua/hyper-chat, default port 16100, password 123456, Web access http://localhost:16100/123456/
• Docker
  • Command line version docker pull dadigua/hyper-chat-mini:1.2.8
  • Ubuntu desktop + Chrome + BrowserUse version (coming soon)
• MCP extension marketplace + third-party MCP support
• Supports free creation and design of Agent, with preset prompts and selection of MCP features
• Supports dark mode🌙
• Resources, Prompts, Tools support
• Supports English and Chinese
• Supports Artifacts, SVG, HTML rendering, js error capture, and opening the Chrome console
• Agent display optimization, supports searching and drag-and-drop sorting
• Supports KaTeX, displays mathematical formulas, code rendering adding highlighting and quick copy
• WebDAV synchronization
• Adds RAG, based on the MCP knowledge base
• Introduces the ChatSpace concept, supports multi-dialogue chatting simultaneously
• Supports Agent Call Agent through HyperAgent's MCP
• Adds scheduled tasks, specifying Agent to complete tasks on time, and view task completion status.

TODO:

• Future versions will include a docker version, integrated Linux desktop, built-in Chrome configuration for remote ports, unified environment, better usability, and web interface control. Usable on any device, including mobile phones.🤣
• Permission pop-up, allow or not
• Implement using LLM to write MCP for itself

LLM

Usage

• 1. Configure APIKEY, make sure your LLM service is compatible with OpenAI style.
• 2. Ensure your system has uv + nodejs installed.

uvx & uv

Install using the command line, or check the official GitHub tutorial uv

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

npx & nodejs

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

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

Development

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

Note

• MacOS encounters a damaged or permission issue, sudo xattr -d com.apple.quarantine /Applications/HyperChat.app
• MacOS nvm users manually input PATH echo $PATH, the Windows version nvm seems to work directly

Telegram

HyperChat User Communication

Call shell mcp

Call terminal mcp, ssh + can execute commands

One-click webpage generation and publish to (cloudflare)

Call Google search, ask it what the TGA Game of the Year is

Organize Zhihu hot searches

Helps you open a webpage, analyze results, and write to a file

Open Baidu and take screenshots

Scheduled task list

MCP market (experimental)

Install MCP interface from the market (experimental)

Install MCP from third parties (supports any MCP)

Install MCP interface from third parties

MCP list (can be dynamically selected)

Render HTML, supports Artifacts, SVG, HTML rendering,

Interface 1

Interface 2

Interface 3, testing model capabilities

Knowledge Base

Disclaimer

• This project is for learning and communication purposes only. If you carry out any operations, such as web scraping, using this project, it is not related to the developers of this project.