#llms

Full-featured MCP support for Ruby and RubyLLM—making it easy to build structured, composable LLM workflows in pure Ruby.

Multi-Provider AI Gateway - No personal logs by design. Model autodiscovery, Failover groups, High availabilty, Android companion app, and more. "Because we have LiteLLM at home"

Ruby's capable AI runtime

Simple, performant, battle-tested framework for building reliable AI applications.

Use Dive to quickly build AI agents in Go. Build agentic CLIs or add AI to your backend Go services. Easily customized and embedded in larger applications.

MkDocs plugin to generate an /llms.txt file (https://llmstxt.org/).

Use Dive to quickly build AI agents in Go. Build agentic CLIs or add AI to your backend Go services. Easily customized and embedded in larger applications.

Agentic First OpenAPI Documentation. Works 100% offline, straight from disk, shareable or publisable to any static host. AI and agent output built in, Built in API Catalog generation.

Training/Fine-tuning at the speed of light

A convenient CLI to streamline LiteRT related development workflows, including converting, quantizing, compiling, managing, running, benchmarking and visualizing LiteRT (TFLite) models on various hardwares (CPU / GPU / NPU) across platforms (desktop, mobile or cloud).

Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.

Docusaurus plugin for generating LLM-friendly documentation following the llmstxt.org standard

A PHP library for writing, reading, and validating llms.txt Markdown files.