Set up models and keys
Choose which models Chat can use, store their API keys safely, and check that they answer. Keys are kept in your operating system’s keychain, never in the vault.
Engine
Section titled “Engine”New chats use Rhizome’s own engine (ADR-0187). Set up the models below in Settings → AI Agents.
Add a provider
Section titled “Add a provider”Settings → AI Agents has three tabs. Local model is for models on your computer. API model is for hosted models and holds Taproot.
| Kind | Examples | Needs |
|---|---|---|
| Hosted | OpenAI, Anthropic, Gemini, OpenRouter, Groq, Mistral | API key, model ID |
| Local | Ollama, LM Studio | Base URL, model ID, usually no key |
| Your own | Any OpenAI-compatible server | Base URL, model ID, optional key and headers |
Anthropic models are not offered by Rhizome’s own engine yet.
Store the key
Section titled “Store the key”Under API key storage, pick one per provider:
- Save locally in Rhizome (recommended). Paste the key. Rhizome stores it in the system keychain: macOS Keychain, Windows Credential Manager, or Secret Service on Linux. Keys that older versions saved in a settings file move to the keychain the first time they’re read.
- Read from env var. Give the variable’s name. Rhizome reads the key from it.
- No key. For local servers that don’t need one.
Don’t edit a key file by hand.
Test the connection
Section titled “Test the connection”Click Test model on the provider. It sends one short request with no tools. If it passes, Settings says “Connection works. The model replied successfully.”
Use free models
Section titled “Use free models”Taproot, the free automatic router on the API model tab, lets Rhizome pick free hosted models for you and move on when one runs out. Each free provider needs its own key. See Free models and routing.
Pick the model for Chat
Section titled “Pick the model for Chat”Choose a model, or Taproot, in the picker. The choice is saved with your settings.