Adds vector embeddings with HNSW indexing to Claude for semantic search and pattern matching. The standout feature is 75x speedup when paired with agentic-flow's ONNX integration, plus you get sql.js persistence that works cross-platform through WASM. Supports hyperbolic embeddings for hierarchical data, which is genuinely useful if you're organizing knowledge graphs or taxonomies. The quantization options (binary at 32x memory reduction) make it viable for running locally without eating your RAM. Skip it for exact text matching, but if you need semantic similarity queries or want to search a knowledge base by meaning rather than keywords, this handles the annoying indexing work for you.
npx skills add https://github.com/ruvnet/ruflo --skill embeddings