Serge

github.com/serge-chat/serge

Serge is a self-hosted chat interface for running large language models using llama.cpp. It stores chat history and parameters in Redis and provides a SvelteKit frontend with a FastAPI and LangChain backend.

AI named Serge from December 2025 to July 2026.

Serge in AI’s own words

Question: What's a good, self-hosted platform for running and managing multiple open-source LLMs locally?

Google AI ModeJul 10, 2026

Serge: A Docker-based frontend that allows you to download and run various models

Ask Google AI Mode yourself (opens in a new tab)

Markets

LLM Fine-Tuning and Hosting Platforms