RubyLLM provider for girb (AI-powered IRB assistant). Install this gem to use OpenAI, Anthropic, Gemini and other LLMs via RubyLLM as your LLM backend.

HTM (Hierarchical Temporal Memory) provides intelligent memory/context management for LLM-based applications. It implements a two-tier memory system with durable long-term storage (PostgreSQL) and token-limited working memory, enabling applications to recall context from past conversations using RAG (Retrieval-Augmented Generation) techniques.

A multi-language code generator to cope with Hyrum's law

A durable, resumable turn pipeline behind an OpenAI-Responses-compatible HTTP API, plus a web control UI. Tools, skills, cross-session memory, per-agent policy, content-safety guardrails — one gem, five shapes: reply in-process, serve, rack_app mounted, embed(backend:).

Agents that write and execute Ruby code. Developers can build and distribute Agents as files or compiled jar files. Inspired by smolagents. LLMs write executable code, not JSON blobs.

An open-source, security-first AI agent framework in Ruby with capability-based permissions, sandboxed skills, and a layered prompt system.

Used in conjunction with the Language Operator for Kubernetes

Interact with PostgreSQL, MySQL, and Oracle databases using natural language. Powered by RubyLLM with a locally-running Ollama model.

Mountable Rails engine that provides hierarchical LLM call tracing and versioned prompt management with Mustache templates.

Build composable LLM workflows using Unix pipe philosophy. Each pipe is a YAML-configured LLM call that communicates via stdin/stdout.

A Ruby gem for translating Markdown files using AI while preserving formatting

Locallingo extends i18n-tasks with AI translation (via RubyLLM — OpenAI, Anthropic, and more), source-hash drift detection so only missing/changed keys are re-translated, and a static + AI translation-quality linter. Everything app-specific — target locales, provider/model, prompt context and glossary, per-language style guides, which validators and quality rules run, and post-translate hooks — is config-driven via `.locallingo.yml`, with a default block plus optional per-package overrides. Ships the `lingo` CLI.

MARS (Multi-Agent Ruby SDK) provides a comprehensive framework for developers to implementmulti-agent solutions using pure Ruby. It offers a simple API for orchestrating multiple agents.

Mildred power organizer

A minimalist AI agent framework with multi-channel support, tool calling, and extensible architecture

An opinionated, drop-in agent harness for RubyLLM. Nexo composes the RubyLLM ecosystem into one coherent front door, adding a Sandbox+Permissions seam and a WorkflowRun lifecycle primitive.

A light agent framework on top of RubyLLM. An agent is an object: its fields are state, its methods are what the model can call, and the methods it declares without a body are written by the model at runtime — the method name and prompt are the specification, the schema is the contract. The model acts by writing Ruby that runs on the agent itself.

Agent framework for Rails: bounded tool-calling loops, fast paths, structured extraction, and (v0.2) durable workflows on ActiveRecord. Built on ruby_llm.

Phronomy is a Ruby AI agent framework that provides composable building blocks — Agents, Workflows, Tools, Filters, and Tracing — for building AI agents in Ruby. Powered by RubyLLM for LLM abstraction.

pikuri-core is the lean, audit-friendly foundation of the pikuri family: Pikuri::Agent (a thin wrapper around ruby_llm's chat loop) with its Configurator + Extension protocol, the strict Pikuri::Tool framework, a listener surface for rendering / budgets / sub-agents, and four bundled stateless tools (calculator, web search, web scrape, fetch). Extensions (skills, MCP, workspace, coding stack, named-agent personas) live in sibling gems so a privacy-conscious user can install just this core and audit a minimal dependency tree. For the convenience bundle that pulls in everything, see the +pikuri+ metagem.