FactDb implements the Event Clock concept - capturing organizational reasoning through temporal facts with validity periods (valid_at/invalid_at), entity resolution, and audit trails back to source content. Built on PostgreSQL with pgvector support for semantic search.

A collection of utilities and enhancements for Rails applications including database optimizations, background processing helpers, and developer tools.

Maglev provides safe structured queries, semantic retrieval, and bounded hybrid workflows over registered ActiveRecord resources.

Under development. Contributors welcome.

Add semantic search and AI-powered chat to any ActiveRecord model. Uses pgvector for vector storage, OpenAI for embeddings, and your existing PostgreSQL database.

Rails AI Kit provides AI building blocks for Rails apps: embeddings (OpenAI, Cohere), vector-based classification, similarity search, and generators. Start with the Classifier feature; more capabilities as the gem grows.

MCP server that indexes codebases using AST-aware chunking and vector embeddings, providing semantic search for Claude Code and other MCP clients.

A read-only, retrieval-grounded chat assistant for Spree storefronts — answers customer questions about the menu, ingredients, dietary info, hours, and policies using the store's own synced catalog and Spree::Policy content. No cart or order mutation capability of any kind. Companion extension to...

Full-text, vector, and hybrid search for ActiveRecord, without leaving SQLite. sqlite_search gives a model full-text search (FTS5 with BM25 ranking), vector search (sqlite-vec through the neighbor gem, with your app supplying embeddings), and hybrid search that fuses the two with Reciprocal Rank ...