@dadigua/hyper-chat NPM

Introduction

HyperChat is an open-source chat client that supports MCP and can use various LLM APIs to achieve the best chat experience, as well as implement 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:

🪟Windows + 🍏MacOS + Linux
Command-line run, 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)
WebDAV supports incremental synchronization, fastest synchronization through hash.
HyperPrompt prompt syntax supports variables (text + js code variables), basic syntax checking + Hover real-time preview.
MCP extensions
Supports dark mode🌙
Resources, Prompts, Tools support
Supports English and Chinese
Supports Artifacts, SVG, HTML, Mermaid rendering
Supports defining Agents, allowing preset prompts and selecting permitted MCP
Supports scheduled tasks, specifying Agents to complete tasks on schedule, and viewing task completion status.
Supports KaTeX, displays mathematical formulas, code rendering increases highlight and quick copy
Added RAG, based on MCP knowledge base
Introduced the ChatSpace concept, supports simultaneous chats across multiple dialogues
Supports chat model selection comparison

TODO:

Implement multi-Agent interactive 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 easy to use
qwen	⭐⭐⭐⭐	Quite useful
doubao	⭐⭐⭐	Feels okay to use
deepseek	⭐⭐⭐⭐	Recently improved

Usage

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

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 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

HyperChat User Communication

Super input, supports variables (text + js code variables), basic syntax checking + Hover real-time preview

Chat supports model selection comparison

image_2025-04-07_21-26-19

Supports clicking tool names for direct debugging

MCP calling Tool prompts + dynamically modifying LLM calling Tool parameters

Supports @ quick input + calling Agent

Supports rendering `Artifacts`, `SVG`, `HTML`, `Mermaid`

Supports MCP selection + selecting partial Tool

You can access from anywhere and any device via the web, and set a password

Calls terminal MCP to automatically analyze asar files + helps me unzip

Calls terminal, compiles and upgrades nginx

Gaode Map MCP

One-click webpage creation, and publish to (cloudflare)

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

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

Opens a webpage for you, analyzes the results, and writes to a file

Through web tools + command line tools, opens GitHub README to learn + GIT clone + set up development environment

Multi-chat Workspace + Night Mode

Scheduled task list + schedules messages to be sent to Agent to complete tasks

Install MCP from third parties (supports any MCP)

H5 interface

Testing model capabilities

Knowledge base

Disclaimer

This project is for learning and communication purposes only. If you use this project for any operations, such as crawling behavior, it has nothing to do with the developers of this project.