@dadigua/hyper-chat

中文 | English

Introduction

HyperChat is an open-source Chat client that supports MCP and can use various LLM APIs to provide the best Chat experience and productivity tools.

• Supports OpenAI-style LLMs: OpenAI, Claude, Claude(OpenAI), Qwen, Deepseek, GLM, Ollama, xAI, Gemini.
• Fully supports MCP.

DEMO

• HyperChat on Nodejs
• Docker on ClawCloud

Features:

• [x] 🪟Windows + 🍏MacOS + Linux
• [x] Command-line run, npx -y @dadigua/hyper-chat, default port 16100, password 123456, Web access http://localhost:16100/123456/
• [x] Docker
  • Command-line version docker pull dadigua/hyperchat-mini:latest
  • Ubuntu desktop + Chrome + BrowserUse version (coming soon)
• [x] WebDAV supports incremental synchronization and fastest sync via hash.
• [x] HyperPrompt syntax supports variables (text + js code variables), basic syntax checking + Hover live preview.
• [x] MCP extension
• [x] Supports dark mode 🌙
• [x] Supports Resources, Prompts, Tools
• [x] Supports English and Chinese
• [x] Supports Artifacts, SVG, HTML, Mermaid rendering
• [x] Supports defining Agents, allows preset prompts, and choose allowed MCP
• [x] Supports scheduled tasks, specify Agents for scheduled tasks, and check task completion status.
• [x] Supports KaTeX, displays mathematical formulas, and code rendering enhances highlighting and quick copying
• [x] Add RAG, based on MCP knowledge base
• [x] Introduce ChatSpace concept, supports multi-chat concurrently
• [x] Supports model comparison selection for chat

TODO:

• Implement a multi-Agent interaction system.

LLM

LLM	Usability	Remarks
claude	⭐⭐⭐⭐⭐⭐	No explanation
openai	⭐⭐⭐⭐⭐	Also perfectly supports multi-step function calls (gpt-4o-mini can also)
gemini flash 2.5	⭐⭐⭐⭐⭐	Very useful
qwen	⭐⭐⭐⭐	Very useful
doubao	⭐⭐⭐	Feels alright to use
deepseek	⭐⭐⭐⭐	Recently improved

Usage

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

uvx & uv

Install via command line, or check the official Github tutorial uv

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

npx & nodejs

Install via command line, or download and install from the official website, 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

HyperChat User Communication

• Telegram
• QQ Group

Super Input, supports variables (text + js code variables), basic syntax checking + Hover live preview

Chat supports model comparison selection

Supports clicking tool names for direct invocation and debugging

MCP calls tool hints + dynamic modification of LLM call tool parameters

Supports @ quick input + Agent invocation

Supports Artifacts, SVG, HTML, Mermaid rendering,

Supports MCP selection + selection of specific Tools

You can access it anywhere + on any device via Web and set a password

Calls terminal MCP to automatically analyze asar files + helps to decompress

Calls the terminal to view the interface

Gaode Map MCP

One-click webpage writing and publishing to (cloudflare)

Calls Google search, asking what the TGA Game of the Year is

What limited-time free games are available? Please visit the website and call the tool

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

Uses web tools + command-line tools to open Github README learning + GIT clone + set up development gold

Multi-chat Workspace + Night mode

Scheduled task list + scheduled messages to Agent to complete tasks

Install MCP from third parties (supports any MCP)

H5 interface

Test model capabilities

Knowledge Base

Disclaimer

• This project is for educational and exchange purposes only. If you use this project for any actions, such as web scraping, it has no relation to the project developers.