HyperChat

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:

• 🪟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.
• 2. Ensure that uv + nodejs is 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 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

Telegram

HyperChat User Communication

            ![image.png](./images/image36.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.