Rails wrapper for langchainrb gem

Plain is an AI and documentation system for rails apps.

The promptcraft CLI let's you replay a conversation between a user and an AI assistant, but with a new system prompt.

RBS type inferrer with LLM

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

Ruby implementation of deepagents - a library for creating deep agents with planning capabilities, sub-agent spawning, and a mock file system

Command line tool for tracking achievments, tasks and interactions. You can add work items, view them and run a webserver to share them with other people, for example via screen sharing. This tool is designed to run in a terminal completely local without sharing any data with any other service. No telemetry, no tracking, no data sharing of any kind.

Declarative agentic framework for LLMs, allowing you to build autonomous agents that can perform complex tasks and interact with the world, without writing code. Agents and skills are defined in markdown files, quite similar to how Github Copilot works. Name is inspired by the English word "helm", which refers to the steering mechanism of a ship, symbolizing guidance and direction. The name also evokes the idea of taking control and navigating through challenges, much like how an agentic framework empowers LLMs to make decisions and take actions autonomously.

Hooks into Langchain.rb methods to capture LLM calls and report them to the Datadog LLM Observability API.

Use this 'compiler' to build software using LLMs in a controlled way. In classical terms, the LLM is the compiler, the context description is the programming language, and the generated output is the binary.

Actionable Agile Metrics and Monte Carlo forecasting engine

Manage AI vector embeddings in C with Ruby integration