Local AI Chat

Run AI models locally with minimal setup. The only requirement is Docker Compose.

Start the stack

Launch Ollama and Open WebUI:

docker compose up -d

Stop everything with:

docker compose down

Download a model

Pull a model inside the Ollama container:

docker exec ollama ollama pull deepseek-r1:8b

Browse available models at https://ollama.com/search

Open the Web UI

Visit http://localhost:3111 in your browser.