Use Ollama (local) in your terminal

Ollama runs models on your own computer, so it’s free and works offline. See the Ollama guide.

Set up

1. Install Ollama from https://ollama.com/download and download a model, for example ollama pull llama3.2.
2. Run kunji keys add ollama. No key is needed; kunji connects to Ollama on your computer.
3. Pick the model you downloaded.
4. Run kunji and start chatting.

Details

Provider id	ollama
Type	Runs locally, no key
API address	http://localhost:11434/v1

Use it

kunji models ollama            # see available models
kunji use ollama:<model>        # make one your default
kunji chat -m ollama:<model>    # or chat with it once

Inside a chat, switch to it with /model ollama:<model>; the conversation carries over.