embeddings

Originally fromruvnet/claude-flow
Installation
SKILL.md

Embeddings Skill

Purpose

Vector embeddings for semantic search and pattern matching with HNSW indexing.

Features

Feature Description
sql.js Cross-platform SQLite persistent cache (WASM)
HNSW 150x-12,500x faster search
Hyperbolic Poincare ball model for hierarchical data
Normalization L2, L1, min-max, z-score
Chunking Configurable overlap and size
75x faster With agentic-flow ONNX integration

Commands

Installs
770
Repository
ruvnet/ruflo
GitHub Stars
59.7K
First Seen
Mar 1, 2026
embeddings — ruvnet/ruflo