Stats
Actions
Tags
From ruflo-agentdb
HNSW vector search with RuVector embeddings for 150x-12500x faster semantic retrieval
How this skill is triggered — by the user, by Claude, or both
Slash command
/ruflo-agentdb:vector-searchThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
HNSW-indexed vector search with RuVector embeddings (384-dim ONNX).
HNSW-indexed vector search with RuVector embeddings (384-dim ONNX).
When you need fast semantic search across large knowledge bases. HNSW provides 150x-12,500x faster search compared to brute-force scanning.
mcp__claude-flow__embeddings_status to verify the embedding enginemcp__claude-flow__embeddings_init if not already activemcp__claude-flow__embeddings_generate for text inputmcp__claude-flow__embeddings_search with a query for semantic matchesmcp__claude-flow__embeddings_compare to measure similarity between textsmcp__claude-flow__memory_search_unified to search across all namespacesFor building custom HNSW indexes:
mcp__claude-flow__ruvllm_hnsw_create — create a new indexmcp__claude-flow__ruvllm_hnsw_add — add vectors to the indexmcp__claude-flow__ruvllm_hnsw_route — route queries through the indexFor hierarchical data (code trees, org charts), use mcp__claude-flow__embeddings_hyperbolic which maps to Poincare ball space.
npx @claude-flow/cli@latest embeddings search --query "authentication patterns"
npx @claude-flow/cli@latest embeddings init
npx @claude-flow/cli@latest memory search --query "your query"
| Method | Speed |
|---|---|
| Brute-force scan | Baseline |
| HNSW (n=500) | 150x faster |
| HNSW (n=10,000) | 12,500x faster |
npx claudepluginhub k2k22k2k22/ruflo --plugin ruflo-agentdbSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.