# Ollama GUI

A modern web interface for chatting with local LLMs served by Ollama, with local chat history, Markdown rendering, dark mode, and a hosted version plus a Docker Compose setup.

Ollama GUI is a web interface for chatting with local large language models through Ollama, storing chat history locally in IndexedDB with full Markdown rendering, a dark mode, and all model processing kept on the local machine for privacy. For local development, a development server includes an automatic proxy that forwards API requests to a local Ollama instance, letting other devices on the same network reach both the UI and the Ollama API; this proxy is development-only and a production deployment needs its own CORS or reverse-proxy configuration.

A hosted version of the interface is also available, used by starting Ollama with a specific `OLLAMA_ORIGINS` value so it accepts requests from that hosted origin. A Docker Compose setup runs Ollama and the GUI together with no separate proxy or CORS configuration needed, downloading models into a local folder, and optionally enabling GPU access.

It is written in Vue and MIT licensed.

Website: https://ollama-gui.vercel.app/