A highly parallel Perl 5 interpreter written in Rust
Scan codebases for embedded authorization logic and generate Policy as Code (Rego for OPA, Cedar for AWS Verified Permissions and other Cedar-compatible engines)
Blazen - A Rust-native AI workflow engine with event-driven orchestration
Structural codebase index for LLM tooling — query definitions, call graphs, and imports without embeddings.
Type-state authorization for MCP tool servers — compile-time proof that auth checks cannot be skipped
Dictator - structural linter framework with native and WASM decree support
A CLI & TUI file aggregator and formatter
RIG-based agentic workflow for LLM orchestration with GLM/Claude
Semantic code analysis CLI for the AI era — powered by DataGrout
Multi-language semantic code analysis library — tree-sitter fact extraction for DataGrout Invariant
Classify code changes by semantic impact — CI-native code review triage
Classification engine for semantic code change analysis — 231 rules, 15 languages, Tree-sitter AST
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.
A compact Ruby DSL for building standards-oriented JSON Schema documents from Ruby.
A Ruby client for the Model Context Protocol (MCP) that seamlessly integrates with RubyLLM. Supports both native full-featured implementation and the official mcp-sdk gem. Connect to MCP servers via SSE, stdio, or HTTP transports, automatically convert MCP tools into RubyLLM-compatible tools, and enable AI models to interact with external data sources and services. Makes using MCP with RubyLLM as easy as possible.
A client to interact with LLM APIs in a consistent way.
Provides a unified adapter using RubyLLM to access OpenAI, Anthropic, Gemini, Bedrock, Ollama, and more through a single interface in DSPy.rb projects.
Rails instrumentation for RubyLLM
A Rails engine for creating, managing, and monitoring LLM-powered agents. Includes a DSL for agent configuration, execution tracking, cost analytics, and a mountable dashboard UI.
Tribunal provides tools for evaluating LLM outputs, detecting hallucinations, measuring response quality, and ensuring safety. Features deterministic assertions, LLM-as-judge evaluations, red team attack generation, and multiple output formats. A RubyLLM plugin inspired by the Elixir Tribunal library.
Monitoring engine for RubyLLM
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.
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.
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.