An RFCXML (RFC 799x) generating backend for Thomas Leitner's "kramdown" markdown parser. Mostly useful for RFC writers.

Professional grade APNs and GCM for Ruby

multi-layer client for the github api v3

This is an update to the old `gem mirror` command. It uses net/http/persistent and threads to grab the mirror set a little faster than the original. Eventually it will replace `gem mirror` completely. Right now the API is not completely stable (it will change several times before release), however, I will maintain stability in master.

Fork of the sauce Ruby gem

Ruby client for using split SDK.

Firebase Cloud Messaging API wrapper for ruby, supports HTTP v1. And including access_token Auto Refresh feature!

Executes SPARQL queries and updates against a remote SPARQL 1.0 or 1.1 endpoint, or against a local repository. Generates SPARQL queries using a simple DSL. Includes SPARQL::Client::Repository, which allows any endpoint supporting SPARQL Update to be used as an RDF.rb repository.

This tool will help manage the content of a Looker instance.

GraphQL client on Rails + Convention over Configuration = ❤️

Ruby client for getstream.io service

Fluentd pluging (fluent.org) for output to Logz.io (logz.io)

Ruby client for Stream Chat.

Android Push Notification in Ruby: simple, fast, high-quality client for FCM (Firebase Cloud Messaging)

multi-layer client for the github api v3

A Vagrant plugin to install Puppet modules using Librarian-Puppet.

Ruby driver for FaunaDB.

The Files.com Ruby client.

Fluentd pluging (fluentd.org) for output to loggly (loggly.com)

llm.rb is a Ruby-centric toolkit for building real LLM-powered systems — where LLMs are part of your architecture, not just API calls. It gives you explicit control over contexts, tools, concurrency, and providers, so you can compose reliable, production-ready workflows without hidden abstractions. Built for engineers who want to understand and control their LLM systems. No frameworks, no hidden magic — just composable primitives for building real applications, from scripts to full systems like Relay. ## Key Features - **Contexts are central** — Hold history, tools, schema, usage, cost, persistence, and execution state - **Tool execution is explicit** — Run local, provider-native, and MCP tools sequentially or concurrently - **One API across providers** — Unified interface for OpenAI, Anthropic, Google, xAI, zAI, DeepSeek, Ollama, and LlamaCpp - **Thread-safe where it matters** — Providers are shareable, while contexts stay isolated and stateful - **Production-ready** — Cost tracking, observability, persistence, and performance tuning built in - **Stdlib-only by default** — Runs on Ruby standard library, with optional features loaded only when used ## Capabilities - Chat & Contexts with persistence - Streaming responses - Tool calling with JSON Schema validation - Concurrent execution (threads, fibers, async tasks) - Agents with auto-execution - Structured outputs - MCP (Model Context Protocol) support - Multimodal inputs (text, images, audio, documents) - Audio generation, transcription, translation - Image generation and editing - Files API for document processing - Embeddings and vector stores - Local model registry for capabilities, limits, and pricing