A framework for building agentic AI workers.

An elegant Ruby SDK for building AI Ruby Agent that interact with both LLMs and system tools

Reviews self-hosted GitLab merge requests with a two-pass LLM pipeline: the first pass finds candidate findings, the second one critiques them and drops the weak ones. Supports Gemini, Ollama, OpenAI, Anthropic, OpenRouter and OpenAI-compatible servers, Jev as the critic, optional Jira context and posting a single updatable review note back to the merge request.

A terminal-friendly interface for interacting with LLM models

Call LLMs from Axn actions using RubyLLM, with structured error handling, schema-based structured output, and cost/token tracking.

A minimal Ruby gem for building agentic AI applications using the ReAct (Reasoning + Acting) loop pattern

A small Ruby CLI that answers questions about a knowledge-brain vault. Retrieval shells out to the hitgate `rag-query` CLI (JSON mode, argv-array, no shell interpolation); the chat is RubyLLM, with retrieved chunks injected as context and cited in the reply.

Brakeman detects security vulnerabilities in Ruby on Rails applications via static analysis.

Production-grade coding agent with tool execution, middleware pipeline, context compaction, session persistence, and multi-provider LLM support.

A comprehensive Ruby SDK for interacting with Buda.com cryptocurrency exchange API with debugging, error handling, and comprehensive examples

A unified platform for knowledge, task management, and chat communication with AI Agents

see http://cpee.org

Envoy is a mountable Rails engine for governed, tool-calling agent chat: a DSL for host-owned toolsets, guard hooks for authorizing every tool call, persisted conversations, and a debug console.

A Ruby gem for identifying birds from photos and audio using RubyLLM. Adds multi-modal identification, location-aware results, multi-model consensus, and a Rails integration.

FlowEngine provides a DSL for defining multi-step flows as directed graphs with conditional branching, an AST-based rule evaluator, and a pure-Ruby runtime engine. No framework dependencies.

Agents that write and execute Ruby code. Inspired by smolagents. LLMs write executable code, not JSON blobs.

Automatically generates Claude Code SKILL.md files from a gem's README, RubyDoc, and changelog. Skills are cached in ~/.gem/skills and symlinked into projects driven by Gemfile.lock. Provides both 'gem skill' and 'bundle skill' subcommands.

Define a safe component catalog, expose it as a RubyLLM tool schema, validate model-generated component trees, and render them with Rails partials, ViewComponent, or JSON.

Genie CLI is a command-line tool that brings Test Driven Development (TDD) principles to life by integrating with a large language model (LLM) through the ruby_llm library. It provides an interactive session to write tests, implement code, and manage your codebase.

Genie CLI is a command-line tool that brings Test Driven Development (TDD) principles to life by integrating with a large language model (LLM) through the ruby_llm library. It provides an interactive session to write tests, implement code, and manage your codebase.