Build AI features the Ruby way. A delightful Ruby AI framework that feels at home in Rails: switch models without rewriting your code, then scale from a single call to production agents, RAG, and workflows. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Azure, Anthropic, Google Gemini, Vertex AI, AWS Bedrock, xAI, Cohere, DeepSeek, Mistral, Perplexity, OpenRouter, ElevenLabs, Deepgram, Ollama and GPUStack (local models), and any OpenAI-compatible API. Plain Ruby with a small set of runtime dependencies.

Forwards RubyLLM::Schema to Schematist::Schema. Depend on schematist instead.

A light agent framework on top of RubyLLM. An agent is an object: its fields are state, its methods are what the model can call, and the methods it declares without a body are written by the model at runtime — the method name and prompt are the specification, the schema is the contract. The model acts by writing Ruby that runs on the agent itself.

A mode is the configuration of one turn: a RubyLLM agent with a routing description. Declare the modes, a fallback, and a classifier; before each answer the router returns a Route that says which mode takes the turn, why, and what the classifier actually said.