Skip to content

HyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.

License

Notifications You must be signed in to change notification settings

BigSweetPotatoStudio/HyperChat

Repository files navigation

中文 | English

Features

HyperChat is an open Chat client that utilizes various LLM APIs to provide the best Chat experience and enables productivity tools through the MCP protocol.

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

MCP:

Build

  • 🪟Windows + 🍏MacOS
  • Supports nvm, see below
  • Resources support
  • Partial Prompts support
  • Tools support
  • Supports English and Chinese
  • Added built-in MCP client hypertools, fetch + search
  • Supports Bot, allows preset prompts and permitted MCP services
  • Supports Artifacts, SVG, HTML rendering, JavaScript error capture, supports opening Chrome console
  • Bot display optimization, supports search and drag-and-drop sorting
  • Supports KaTeX, displays math formulas, code rendering includes highlighting and quick copy
  • WebDAV synchronization
  • MCP extension marketplace + third-party MCP support
  • Added RAG, based on MCP knowledge base
  • Introduced ChatSpace concept, supports multiple conversations simultaneously

TODO:

  • Permission prompt, whether to allow
  • Add task concept. Agent Administrator, manage Task through Administrator.
  • Implement LLM writing tools for itself
  • Local shell + nodejs + js on web runtime environment

LLM

LLM Usability Remarks
claude ⭐⭐⭐⭐⭐ No explanation
openai ⭐⭐⭐⭐🌙 Also can perfectly support multi-step function calls (gpt-4o-mini can too)
qwen ⭐⭐⭐⭐🌙 Very usable, feels better than OpenAI
doubao ⭐⭐⭐ Okay to use
deepseek ⭐⭐ Multi-step function calls may have issues

Usage

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

Install using command line, or refer to the official GitHub tutorial uv

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

Install using command line, or go to the official website to download, official site nodejs

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

Development

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

Note

  • On MacOS, if you encounter issues with corrupt files or permissions, use sudo xattr -d com.apple.quarantine /Applications/HyperChat.app
  • For MacOS nvm users, manually input PATH echo $PATH, the Windows version of nvm seems to work directly

image.png

Telegram

HyperChat User Communication

image.png

image.png

image.png

image.png

image.png

image.png

image.png

image.png

image.png

image.png

image.png

image.png

image.png

image.png

image.png

Disclaimer

  • This project is for educational and communication purposes only. If you use this project for any actions, such as web scraping, it is unrelated to the developers of this project.

About

HyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published