Product Information
What is Serge?
Serge is a chat interface built with llama.cpp for running GGUF models. No API keys required, fully self-hosted!
SvelteKit frontend
Redis for storing chat history and parameters
FastAPI + LangChain for the API, utilizing Python bindings to wrap llama.cpp calls
How to use Serge?
Serge is a chat interface built on llama.cpp for running GGUF models, serving as a fully self-hosted personal assistant with no reliance on remote APIs, data collection, or ads.
Core Functions of Serge
Nginx
Docker support
Usage Scenarios of Serge
- Use as a personal self-hosted assistant.
- Run GGUF models for local chat interactions.
- Store and manage chat history and parameters.
- Deploy via Docker to converse with AI in local environments.
Common Questions about Serge
What does Serge do?
How do I use Serge?
What are the core functionalities of Serge?
What are the application scenarios of Serge?



















