Skip to main content

Supported providers

This is a list of our currently supported providers.

  • OpenAI
  • Ollama
  • Mock

If you need another integration you can open a PR for it!

OpenAI

Requires the openai gem and an API key:

OPENAI_ACCESS_TOKEN=your_api_key_here
provider :openai, model: "gpt-4o-mini"

Ollama

Talks to a local (or remote) Ollama server via its OpenAI-compatible /v1 endpoint. Depends on the openai gem too — no separate client library needed. Pick a tool-calling-capable model (e.g. llama3.1, qwen2.5) if your agent uses tools.

provider :ollama, model: "llama3.1"

Configuration is via environment variables, all optional:

VariableDefaultPurpose
OLLAMA_HOSThttp://localhost:11434Base URL of the Ollama server (the provider appends /v1)
OLLAMA_MODELllama3.1Default model when none is passed to provider/use_model
OLLAMA_API_KEYollamaSent as the bearer token; Ollama ignores it, but the openai client requires a non-nil value

Streaming and tool-calling both work the same as the OpenAI provider (Ollama subclasses it and only overrides client construction and defaults).

Mock

Returns a canned response without making network calls. Useful for tests.