J
HyperChat
Created Oct 19, 2025
by
BigSweetPotatoStudio
Categories
Language:
JavaScript
Stars:
478
Forks:
50
README
Introduction
HyperChat is an open-source Chat client that supports MCP and can use APIs from various LLMs to achieve the best Chat experience and productivity tools.
- Supports OpenAI-style LLMs,
OpenAI,Claude(OpenRouter),Qwen,Deepseek,GLM,Ollama. - Fully supports MCP.
DEMO
- HyperChat on Docker
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)
- Command line version
- [x]
WebDAVsupports incremental sync - [x] Added
HyperPromptprompt syntax, supports variables (text + js code variables), basic syntax checking + hover real-time preview. - [x]
MCPextension - [x] Supports dark mode🌙
- [x] Resources, Prompts, Tools support
- [x] Supports English and Chinese
- [x] Supports
Artifacts,SVG,HTML,Mermaidrendering - [x] Supports defining Agents, with preset prompts and options for allowed MCPs
- [x] Supports scheduled tasks, specifying Agents to complete tasks on a schedule and view task completion status.
- [x] Supports
KaTeX, displaying mathematical formulas, code rendering with syntax highlighting and quick copy - [x] Added
RAG, based on MCP knowledge base - [x] Introduced ChatSpace concept, supporting simultaneous chats in multiple conversations
- [x] Supports model comparison in chat
TODO:
- Support official Claude protocol
LLM
| LLM | Usability | Remarks |
|---|---|---|
| claude | ⭐⭐⭐⭐⭐ | No explanation |
| openai | ⭐⭐⭐⭐ | Also supports multi-step function calls perfectly (gpt-4o-mini also works) |
| gemini flash 2.0 | ⭐⭐⭐⭐ | Very usable |
| qwen | ⭐⭐⭐⭐ | Very usable |
| doubao | ⭐⭐⭐ | Feels okay to use |
| deepseek | ⭐⭐⭐ | Multi-step function calls may have issues |
Usage
-
- Configure API KEY, ensure your LLM service is compatible with OpenAI style.
-
- Ensure that
uv + nodejsand others are installed on your system.
- Ensure that
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
Telegram
Super input, supports variables (text + js code variables), basic syntax checking + hover real-time preview
Chat supports model comparison
Click tool names to directly invoke debugging
MCP call Tool prompt + dynamically modify LLM call Tool parameters
Supports quick input with @ + invoking Agent
Supports Artifacts, SVG, HTML, Mermaid rendering
Supports selecting MCP + selecting part of Tool
You can access via the Web anywhere + any device, and set a password
Calling terminal MCP automatically analyzes ASAR files + helps decompress them
Calling terminal view interface
Gaode Map MCP
One-click webpage writing and publishing to (cloudflare)
Calling Google Search, asking what the TGA Game of the Year is
What are some limited-time free games, please visit the website to call the tool
Helps you open web pages, analyze results, and write to files
Using web tools + command line tools to open GitHub README for learning + GIT clone + setting up development environment
Multi-chat Workspace + Night mode
Scheduled task list + schedule sending messages to Agent to complete tasks
Install MCP from third-party (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 is unrelated to the developers of this project.
Last updated: Oct 19, 2025