Unclaimed project
Are you a maintainer of ruby_llm? Claim this project to take control of your public changelog and roadmap.
Changelog
One beautiful Ruby API for OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, DeepSeek, Ollama, VertexAI, Perplexity, Mistral, xAI, GPUStack & OpenAI compatible APIs. Chat, Vision, Audio, PDF, Images, Embeddings, Tools, Streaming & Rails integration.
This release welcomes xAI as a first-class provider, brings Grok models into the registry, and polishes docs around configuration and thinking. Plug in your xAI API key and start chatting with Grok in seconds.
Use xAI’s OpenAI-compatible API via a dedicated provider and jump straight into chat:
This release brings first-class extended thinking across providers, full Gemini 3 Pro/Flash thinking-signature support (chat + tools), a Rails upgrade path to persist it, and a tighter streaming pipeline. Plus official Ruby 4.0 support, safer model registry refreshes, a Vertex AI global endpoint fix, and a docs refresh...
A small patch that swaps the model registry backend, updates Imagen defaults, and smooths out migrations and local setup—plus a couple of linting/test adjustments.
This is a big deal for RubyLLM. Switching the registry to Models.dev fixes every issue we've had with model metada...
A focused patch release that keeps ActiveRecord integrations humming in namespaced apps, restores Anthropic uploads, and hardens Vertex AI auth while smoothing out MySQL migrations and attachment handling.
acts_as_* helpers now accept explicit foreign key over...
Major release that makes tool definitions feel like Ruby, lets you lean on Anthropic prompt caching everywhere, and turns audio transcription into a one-liner—plus better Gemini structured output and Nano Banana image responses.
The new RubyLLM::Schema params DSL supports full JSON...