Embeddings

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.

skills.sh installs: 1.2K
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill embeddings --agent claude-code

Installs into .claude/skills of the current project.

Files

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

Initialize Embeddings

npx claude-flow embeddings init --backend sqlite

Embed Text

npx claude-flow embeddings embed --text "authentication patterns"

Batch Embed

npx claude-flow embeddings batch --file documents.json

Semantic Search

npx claude-flow embeddings search --query "security best practices" --top-k 5

Memory Integration

# Store with embeddings
npx claude-flow memory store --key "pattern-1" --value "description" --embed

# Search with embeddings
npx claude-flow memory search --query "related patterns" --semantic