Ruby gem for running state-of-the-art language models locally. Access LLMs, embeddings, rerankers, and NER models directly from Ruby using Rust-powered Candle with Metal/CUDA acceleration.

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

Gazetteer candidates filtered by a MiniLM + MLP context classifier trained on 491K labeled samples, so prose like 'can-do attitude' doesn't become a skill. Runs on ONNX Runtime via the informers gem.

Hierarchical persistent memory with semantic search for SwarmSDK AI agents