With Ollama • Enkaidu

Start with Ollama

If you have Ollama running, create a file enkaidu.yaml and copy in the following configuration, then run enkaidu from the commandline in the same folder as the config file.

session:
  model: qwen3                # <---
auto_load:
  toolsets:
    - DateAndTime
llms:
  my_ollama:
    provider: ollama
    models:
      - name: qwen3           # <---
        model: qwen3:8b       # <---

If you’re using a different local model, change the values pointed to by the # <--- comment.

Cloud-hosted Ollama models New in 0.9.12

Enkaidu also supports Ollama cloud-hosted models. To use one, set your API key in the OLLAMA_API_KEY environment variable before starting Enkaidu:

export OLLAMA_API_KEY=your-api-key-here

Then reference the cloud model by name in your enkaidu.yaml as shown above. On Windows use set OLLAMA_API_KEY=your-api-key-here (or setx for persistence).