One beautiful Ruby API for GPT, Claude, Gemini, and more. Easily build chatbots, AI agents, RAG applications, and content generators. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Anthropic, Google Gemini, AWS Bedrock, DeepSeek, Mistral, Ollama (local models), OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API. Minimal dependencies - just Faraday, Zeitwerk, and Marcel.

One beautiful Ruby API for GPT, Claude, Gemini, and more. Easily build chatbots, AI agents, RAG applications, and content generators. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Anthropic, Google Gemini, AWS Bedrock, DeepSeek, Mistral, Ollama (local models), OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API. Minimal dependencies - just Faraday, Zeitwerk, and Marcel.

LLM Rescuer uses artificial intelligence to guess what you probably meant when you called a method on nil. Instead of crashing with NoMethodError, it asks GPT to analyze your code and hallucinate a reasonable response. Because clearly, the best way to solve Tony Hoare's billion-dollar mistake is to throw AI at it until it works. What could possibly go wrong? 🎭

One beautiful Ruby API for GPT, Claude, Gemini, and more. Easily build chatbots, AI agents, RAG applications, and content generators. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Anthropic, Google Gemini, AWS Bedrock, DeepSeek, Mistral, Ollama (local models), OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API. Minimal dependencies - just Faraday, Zeitwerk, and Marcel. With additional features from the community.

Wraps RubyLLM::Chat with input/output contracts, business-rule validation, retry with model escalation on validation failure, pre-flight cost ceilings, and an evaluation framework. Sibling abstraction to RubyLLM::Agent — same niche (reusable class-based prompts), wider contract.

RubyLLM::Template provides a flexible template system for RubyLLM, allowing you to organize chat prompts, system messages, and schemas in ERB template files for easy reuse and maintenance.

Provider-neutral LLM primitives, schemas, routing metadata, and shared codecs for LegionIO LLM provider extensions.

Graph-based parallel workflow execution engine for Rails with a React Flow editor, REST API, and extensible plugin system for nodes and triggers.

Probatio Diabolica runs custom *_spec.rb files with a DSL inspired by RSpec and supports text/image/PDF reporting.

RobotLab is a Ruby framework for building and orchestrating multi-robot LLM workflows. Built on ruby_llm, it provides robots with template-based prompts, tools, and shared memory; networks for coordinating multiple robots with intelligent routing; MCP (Model Context Protocol) integration for external tool servers; and a memory system with Redis backend and semantic caching. Optional gems add Rails integration (robot_lab-rails), durable learning (robot_lab-durable), Ractor concurrency (robot_lab-ractor), and document storage (robot_lab-document_store).

LLM evaluation engine for Rails.

Validates and coerces unstructured LLM responses directly into rich, schema-validated Ruby objects with automatic self-correction loops.

A Rails engine providing comprehensive observability for LLM-powered applications. Features include session tracking, trace analysis, prompt management, cost monitoring, and optional chat/agent testing UI (with RubyLLM integration).

Fork of RubyLLM with features to power Swarm, a multi-agent orchestration framework. One beautiful Ruby API for GPT, Claude, Gemini, and more. Easily build chatbots, AI agents, RAG applications, and content generators. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Anthropic, Google Gemini, AWS Bedrock, DeepSeek, Mistral, Ollama (local models), OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API. Minimal dependencies - just Faraday, Zeitwerk, and Marcel.

LLM powered business intelligence. Build SQL reports using natural language.