A RubyLLM plugin that enables local LLM execution using the Red Candle gem. Run quantized GGUF models directly in Ruby without external API calls. Supports streaming, structured output, and multiple model architectures including Gemma, Llama, Qwen, Mistral, and Phi.

Cache RubyLLM responses based on semantic similarity, not exact string matching. Reduces costs and latency by returning cached responses for semantically equivalent queries.

Route messages to specialized RubyLLM chat agents based on semantic similarity using embeddings and kNN lookup

Provides an adapter to integrate RubyLLM with Sequel ORM.

Provides a RubyLLM::Provider that allows you to stub responses for testing purposes. You can stub individual responses or a sequence of responses, and you can also temporarily stub responses within a block.

Intuitive one-liner utility methods for common LLM tasks like text summarization, translation, data extraction, classification, grammar correction, sentiment analysis, key point extraction, text rewriting, and question answering.

ruby_llm-toolbox bundles filesystem, shell, web, git, and data tools as ready-to-use RubyLLM::Tool subclasses. One require loads everything; read-only tools are on by default while mutating/exec tools are gated behind explicit config. Tool output is token-budgeted via ruby_llm-tokenizer.

A RubyLLM plugin that integrates Top Secret to automatically filter sensitive information from LLM interactions.

Automatically report AI agent health, response times, and model info to your ups.dev status page.

LLM powered business intelligence. Build SQL reports using natural language.

A mixin that gives any Ruby class the ability to generate and install methods at runtime via an LLM. Describe what you want in plain English and get a working method back.

SharedTools provides a collection of reusable common tools for Ruby applications using ruby_llm gem.

Stop writing code, let LLMs slop it for your at boot time

A Rails Engine wrapping SmarterCSV for CSV importing with three-tier AI header matching (lookup + vector similarity + LLM fallback), batch processing, and import tracking. Only headers are sent to AI — row data never leaves your application.

Smith is a workflow-first multi-agent orchestration library built on RubyLLM. It provides state machine modeling, typed contracts, budget enforcement, guardrails, and observability for agent workflows.

Solid Agent stores agent runs in its own database and dispatches staged workflow tasks to the RubyLLM runtime with a built-in Rails UI.

Simplistic playpen (e.g. not for serious use) for doing technical analysis of stock prices. Under Construction.

Comprehensive CLI tool for managing Strata Semantic Analytics projects. Create and initialize projects, manage datasource connections, build semantic table models with AI assistance, run audits and validations, and deploy projects to Strata servers. Supports multiple data warehouse adapters including PostgreSQL, MySQL, SQL Server, Snowflake, Athena, Trino, ClickHouse, and more.

Hierarchical persistent memory with semantic search for SwarmSDK AI agents

SwarmSDK is a complete reimagining of Claude Swarm that runs all AI agents in a single process using RubyLLM for LLM interactions. Define collaborative AI agents in simple Markdown files with YAML frontmatter, and orchestrate them without the overhead of multiple processes or MCP inter-process communication. Perfect for building lightweight, efficient AI agent teams with specialized roles and capabilities.