HyperChat
HyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.
claude mcp add --transport stdio bigsweetpotatostudio-hyperchat npx -y @dadigua/hyper-chat \ --env PORT="16100 (default)" \ --env PASSWORD="123456 (default)"
How to use
HyperChat is an open-source MCP-enabled chat client that integrates with multiple LLM APIs (OpenAI-style, including OpenAI, Claude/OpenRouter, Qwen, Deepseek, GLM, Ollama) and a rich set of productivity tools. It supports MCP extensions, agents, prompts, WebDAV sync, and advanced rendering (KaTeX, SVG, Mermaid) with a focus on multi-channel conversations via the HyperChat interface. You can run it locally using npx or via Docker, and connect MCP tools to orchestrate tasks across different LLMs and agents. Start by launching the server through npx: npx -y @dadigua/hyper-chat, which will boot on port 16100 by default and require a password of 123456 for Web UI access. Once running, you can access the Web UI at http://localhost:16100/123456/ and begin configuring MCP tools, agents, and prompts to orchestrate complex workflows across LLMs. The MCP integration allows you to define Tools and Agents, schedule tasks, and perform MCP calls within chat sessions, enabling advanced automation and knowledge-base-driven interactions. The CLI and web UI together let you manage conversations, render rich content (SVG, Mermaid, KaTeX), and leverage the Prompts/HyperPrompt features for dynamic parameterization and real-time previews.
How to install
Prerequisites:
- Node.js (for optional local npx usage) or Docker if you prefer containerized usage
- Internet access to fetch the package from npm
Option A — Install and run with npx (Node.js):
- Ensure Node.js and npm are installed on your system.
- Open a terminal and run: npx -y @dadigua/hyper-chat
- The server will start on port 16100 by default (adjust via environment if needed). Access the UI at http://localhost:16100/123456/
Option B — Run with Docker (if you prefer containerized deployment):
- Ensure Docker is installed and running.
- Pull and run the HyperChat image: docker pull dadigua/hyperchat-mini:latest docker run -p 16100:16100 -e PORT=16100 -e PASSWORD=123456 --name hyperchat -i dadigua/hyperchat-mini:latest
- Open http://localhost:16100/123456/ in your browser.
Notes:
- Default port is 16100 and default password is 123456; change these in env vars if needed.
- For development, you can clone the repository and run npm install then npm run dev as described in the project docs.
Additional notes
Tips and caveats:
- The MCP extension is built-in; to utilize Tools, Prompts, and Agents, configure MCP definitions within the HyperChat UI or config files provided by the project.
- If you run behind a firewall or require a custom port, adjust the PORT environment variable accordingly.
- When using Docker, ensure the container has network access to fetch LiM APIs if required by prompts.
- Keep an eye on the npm package version (@dadigua/hyper-chat) to stay aligned with MCP extensions and agent definitions.
- If you encounter authentication issues, confirm the Web UI URL and the password format; the default is 123456 unless overridden.
Related MCP Servers
cipher
Byterover Cipher is an opensource memory layer specifically designed for coding agents. Compatible with Cursor, Codex, Claude Code, Windsurf, Cline, Claude Desktop, Gemini CLI, AWS's Kiro, VS Code, Roo Code, Trae, Amp Code and Warp through MCP. Built by https://byterover.dev/
mcp-framework
A framework for writing MCP (Model Context Protocol) servers in Typescript
MCP-Nest
A NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.
mcp-graphql
Model Context Protocol server for GraphQL
mcp-use-ts
mcp-use is the framework for MCP with the best DX - Build AI agents, create MCP servers with UI widgets, and debug with built-in inspector. Includes client SDK, server SDK, React hooks, and powerful dev tools.
mcp-gitlab
Enhanced MCP server for GitLab: group projects listing and activity tracking