ruvector weekly downloads statistics

ruvector

The fastest vector database for Node.js—built in Rust, runs everywhere

Ruvector is a self-learning vector database with enterprise-grade semantic search, hybrid retrieval (sparse + dense), Graph RAG, FlashAttention-3, and DiskANN — all in a single npm package. Unlike cloud-only solutions or Python-first databases, Ruvector is designed for JavaScript/TypeScript developers who need blazing-fast vector search without external services.

🚀 Sub-millisecond queries • 🎯 52,000+ inserts/sec • 💾 ~50 bytes per vector • 🌍 Runs anywhere • 🧠 859 tests passing

Built by rUv with production-grade Rust performance and intelligent platform detection—automatically uses native bindings when available, falls back to WebAssembly when needed.

🌐 Visit ruv.io | 📦 GitHub | 📚 Documentation

---

🧠 Claude Code Intelligence v2.0

Self-learning intelligence for Claude Code — RuVector provides optimized hooks with ONNX embeddings, AST analysis, and coverage-aware routing.

# One-command setup with pretrain and agent generation
npx ruvector hooks init --pretrain --build-agents quality

Core Features

• 🎯 Smart Agent Routing — Q-learning optimized suggestions with 80%+ accuracy
• 📚 9-Phase Pretrain — AST, diff, coverage, neural, and graph analysis
• 🤖 Agent Builder — Generates optimized .claude/agents/ configs
• 🔗 Co-edit Patterns — Learns file relationships from git history
• 💾 Vector Memory — HNSW-indexed semantic recall (150x faster)

New in v2.1 — SOTA Vector Search

• FlashAttention-3 — IO-aware tiled attention, O(N) memory instead of O(N^2)
• Graph RAG — Knowledge graph + community detection for multi-hop queries (30-60% improvement)
• Hybrid Search — Sparse + dense vectors with RRF fusion (20-49% better retrieval)
• DiskANN / Vamana — SSD-friendly ANN graph with PQ compression for large-scale search
• ColBERT Multi-Vector — Per-token late interaction retrieval (MaxSim)
• Matryoshka Embeddings — Adaptive-dimension search with funnel/cascade modes
• MLA — Multi-Head Latent Attention with ~93% KV-cache compression (DeepSeek-V2/V3)
• Mamba SSM — Selective State Space Models for linear-time sequence processing
• TurboQuant — 2-4 bit KV-cache quantization, 6-8x memory reduction
• OPQ — Optimized Product Quantization with learned rotation (10-30% error reduction)
• GraphMAE — Graph Masked Autoencoder for self-supervised node learning

New in v2.0

• ONNX WASM Embeddings — all-MiniLM-L6-v2 (384d) runs locally, no API needed
• AST Analysis — Symbol extraction, complexity metrics, import graphs
• Diff Embeddings — Semantic change classification with risk scoring
• Coverage Routing — Test coverage-aware agent selection
• Graph Algorithms — MinCut boundaries, Louvain communities, Spectral clustering
• 🛡️ Security Scanning — Parallel vulnerability pattern detection
• 🎯 RAG Context — Semantic retrieval with HNSW indexing

Performance

Backend	Read Time	Speedup
ONNX inference	~400ms	baseline
HNSW search	~0.045ms	8,800x
Memory cache	~0.01ms	40,000x

📖 Full Hooks Documentation →

MCP Server Integration

RuVector includes an MCP server for Claude Code with 97 tools:

# Add to Claude Code
claude mcp add ruvector -- npx ruvector mcp start

Available MCP Tools:

• hooks_route, hooks_route_enhanced — Agent routing with signals
• hooks_ast_analyze, hooks_ast_complexity — Code structure analysis
• hooks_diff_analyze, hooks_diff_classify — Change classification
• hooks_coverage_route, hooks_coverage_suggest — Test-aware routing
• hooks_graph_mincut, hooks_graph_cluster — Code boundaries
• hooks_security_scan — Vulnerability detection
• hooks_rag_context — Semantic context retrieval
• hooks_attention_info, hooks_gnn_info — Neural capabilities
• brain_search, brain_share, brain_status — Shared brain knowledge
• decompile_package, decompile_file, decompile_url — Package/file decompilation + witness
• edge_status, edge_join, edge_balance — Edge cluster coordination
• identity_generate, identity_show — Agent identity

See npx ruvector mcp tools for the full, authoritative tool list.

MCP tool-access policy (default-deny, ADR-256): restrict the exposed/callable tool surface with environment variables — useful for least-privilege deployments.

# Only expose specific tools (everything else is denied)
RUVECTOR_MCP_ALLOW="hooks_route,hooks_recall" npx ruvector mcp start

# Block specific tools (deny wins over allow)
RUVECTOR_MCP_DENY="hooks_force_learn" npx ruvector mcp start

# Apply a curated read-only profile (safe, non-mutating subset)
RUVECTOR_MCP_PROFILE=readonly npx ruvector mcp start
```…