Ollama

Run models locally with Ollama.

First, start Ollama and pull a model:

ollama serve
ollama pull qwen3.5:latest

Configure

In the TUI — add or switch providers without restarting:

/provider              # open the picker → Add a profile: kind=ollama, base URL http://localhost:11434/v1, model
/provider use ollama   # switch to a saved profile
/model qwen3.5:latest  # switch model for this session

From the command line — set environment variables:

export YOTTACODE_PROVIDER=ollama
export YOTTACODE_MODEL=qwen3.5:latest
export YOTTACODE_BASE_URL=http://localhost:11434/v1

…or pass flags at launch (they override the environment):

yottacode --provider ollama \
  --model qwen3.5:latest \
  --base-url http://localhost:11434/v1

Ollama does not require an API key. Provider-native hosted tools are not available; the model can use yottacode local tools such as fetch_url for concrete URLs.

xAI OpenAI-compatible