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-minded Chat client that can use APIs from various LLMs to achieve the best Chat experience and implement 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 installation and configuration for MCP, one-click installation, and contributions to HyperChatMCP are welcome.
  • Also supports manual installation of third-party MCPs, just fill in command, args, env.

MCP:

Build

  • 🪟Windows + 🍏MacOS
  • Supports dark mode🌙
  • Supports nvm, see below
  • Supports Resources, Prompts, Tools
  • Supports both English and Chinese
  • Added built-in MCP client hypertools, fetch + search
  • Supports Agent, allowing preset prompts and permissible MCP services
  • Supports Artifacts, SVG, HTML rendering, js error capture, and supports opening Chrome's console
  • Agent display optimization, supports search and drag-and-drop sorting
  • Supports KaTeX, displaying mathematical formulas, code highlighting and quick copy
  • WebDAV synchronization
  • MCP extension market + third-party MCP support
  • Added RAG, based on the MCP knowledge base
  • Introduced the ChatSpace concept, supporting multiple conversations simultaneously
  • Supports Agent Call Agent through HyperAgent's MCP
  • Added scheduled tasks, designating agents to complete tasks on schedule and check task completion status.

TODO:

  • Permission pop-up, to allow or not
  • Implement LLMs writing tools for themselves
  • Local shell + nodejs + js on web runtime environment

LLM

LLM Usability Remarks
claude ⭐⭐⭐⭐⭐ No explanation
openai ⭐⭐⭐⭐⭐ Also supports multi-step function call perfectly (gpt-4o-mini also works)
gemini flash 2.0 ⭐⭐⭐⭐🌙 Very usable
qwen ⭐⭐⭐⭐🌙 Very usable
doubao ⭐⭐⭐ Feels okay to use
deepseek ⭐⭐ Multi-step function call may have issues

Usage

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

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

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

Install using the command line, or download and install from the 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

  • MacOS encounters damage or permission issues, sudo xattr -d com.apple.quarantine /Applications/HyperChat.app
  • MacOS nvm users need to manually enter PATH echo $PATH, windows version nvm seems to be usable 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

image.png

image.png

Disclaimer

  • This project is for learning and communication purposes only. If you use this project for any operations, such as web scraping, etc., the project developers are not responsible.

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