HuggingChat UI

HuggingChat UI is a browser-based ChatGPT alternative for people and teams who want to host their own chat service. It's the application behind Hugging Face's hosted HuggingChat, and it connects to a separate model backend.

• Local and cloud models: Chat with models served by Ollama, llama.cpp server, OpenRouter or Hugging Face Inference Providers through OpenAI-compatible APIs.
• Optional model routing: Omni can route image inputs, tool requests and ordinary messages to different models, with selection handled on your own server.
• MCP tools: Connect MCP servers so compatible models can call tools and use their results in a conversation; the interface displays parameters, progress, results and errors.
• Custom branding: Change the app name, logos and favicons for your own deployment.

The app is open source under Apache 2.0 and can run on your computer or server, including through Docker. It doesn't run models itself. Local inference requires a separate backend on your hardware; cloud backends receive the requests you send them. MCP tool use requires a model with OpenAI function-calling support.

MongoDB stores chat history, user records, settings and files. The database can run locally or use a managed service such as MongoDB Atlas. A Docker image bundles the app with MongoDB. Hugging Face's public HuggingChat runs as a separate hosted service.