HyperChat

中文 | English

Features

HyperChat is an open Chat client that can use APIs from various LLMs, fully supports MCP, and provides the best Chat experience. It also implements a productivity MAX tool based on native Agents.

• Supports OpenAI-style LLMs, OpenAI, Claude(OpenRouter), Qwen, Deepseek, GLM, Ollama.
• Built-in MCP plugin market, user-friendly MCP installation and configuration, one-click installation, contributions to HyperChatMCP are welcome.
• Also supports manual installation of third-party MCPs, simply fill in command, args, and env.

MCP:

• MCP extension market + third-party MCP support
• Supports creating Agent freely, presetting prompts, selecting MCP functionalities
• 🪟 Windows + 🍏 MacOS + Linux + Docker (coming soon)
• Supports dark mode 🌙
• Resources, Prompts, Tools support
• Supports English and Chinese
• Supports Artifacts, SVG, HTML rendering, JS error capturing, and opening Chrome console
• Agent display optimization, supports search and drag-and-drop sorting
• Supports KaTeX, displays mathematical formulas, code rendering with syntax highlighting and quick copy
• WebDAV synchronization
• Add RAG, based on MCP knowledge base
• Add ChatSpace concept, supports multiple conversations at the same time
• Supports Agent calling Agent through HyperAgent's MCP
• Add scheduled tasks, specify Agent to complete tasks at specified times, and view task completion status.

TODO:

            - [ ] A Docker version will be added later, with a built-in Linux desktop and built-in Chrome configure remote ports, unified environment for better usability. Then control via web interface. Usable on any device, including mobile phones 🤣

• Permission pop-up, whether to allow
• Implement LLM writing MCP for itself

LLM

LLM	Usability	Remarks
claude	⭐⭐⭐⭐⭐	No explanation
openai	⭐⭐⭐⭐⭐	Can also perfectly support multi-step function calls (gpt-4o-mini can also)
gemini flash 2.0	⭐⭐⭐⭐🌙	Very useful
qwen	⭐⭐⭐⭐🌙	Very useful
doubao	⭐⭐⭐🌙🌙	Feels okay to use
deepseek	⭐⭐⭐🌙🌙	Multi-step function calls have issues

Usage

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

Notes

• If you encounter a damaged or permission issue on MacOS, run sudo xattr -d com.apple.quarantine /Applications/HyperChat.app
• MacOS nvm users should manually set PATH with echo $PATH, Windows version of nvm seems to work directly

Telegram

            [HyperChat User Communication](https://t.me/dadigua001)

Calling shell MCP

Calling terminal MCP, ssh + can execute commands

One-click web page writing and publishing to (cloudflare)

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

Organizing Zhihu hot searches

Helping you open web pages, analyze results, and write to files

Open Baidu and take a screenshot

Scheduled task list

MCP Market (experimental)

Installing MCP interface from the market (experimental)

Installing MCP from third parties (supports any MCP)

Installing MCP interface from third parties

MCP list (can be dynamically selected)

Rendering HTML, supports Artifacts, SVG, HTML rendering

Interface 1

Interface 2

Interface 3, 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 web crawling behavior, it is not related to the developers of this project.