Linux x64 GNU native module for @ruvector/attention
Windows x64 MSVC native module for @ruvector/attention
macOS Apple Silicon ARM64 native module for @ruvector/attention
macOS Intel x64 native module for @ruvector/attention
Linux ARM64 GNU native module for @ruvector/attention
High-performance WebAssembly attention mechanisms: Multi-Head, Flash, Hyperbolic, MoE, CGT Sheaf Attention with GPU acceleration for transformers and LLMs
High-performance attention mechanisms with 7 mathematical theories: Optimal Transport, Mixed Curvature, Topology, Information Geometry, Information Bottleneck, PDE/Diffusion, Unified Diagnostics
High-performance WebAssembly attention mechanisms: Multi-Head, Flash, Hyperbolic, MoE, CGT Sheaf Attention with GPU acceleration for transformers and LLMs
Unified WebAssembly bindings for 18+ attention mechanisms: Neural, DAG, Graph, and Mamba SSM
Graph Neural Network capabilities for Ruvector - Node.js bindings
Proof-gated graph transformer with 8 verified modules — physics, biological, manifold, temporal, economic graph intelligence via NAPI-RS
WASM bindings for ruvector-graph-transformer: proof-gated graph attention in the browser
Self-learning vector database for Node.js — hybrid search, Graph RAG, FlashAttention-3, HNSW, 50+ attention mechanisms
Unified WebAssembly bindings for 18+ attention mechanisms: Neural, DAG, Graph, and Mamba SSM
Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference
High-performance vector database with HNSW indexing - 50k+ inserts/sec, built in Rust for AI/ML similarity search and semantic search applications
Portable WASM embedding generation with SIMD and parallel workers - run text embeddings in browsers, Cloudflare Workers, Deno, and Node.js
RuVector Format Node.js native bindings
RVF self-learning temporal solver — Thompson Sampling, PolicyKernel, ReasoningBank
Complete WASM toolkit for edge AI: vector search, graph DB, neural networks, DAG workflows, SQL/SPARQL/Cypher, and ONNX inference - all running in browser
Native Node.js bindings for RuVector Graph Database with hypergraph support, Cypher queries, and persistence - 10x faster than WASM
RuVector Format — unified TypeScript SDK for vector intelligence
RuVector Format WASM microkernel for browser and edge vector operations
WASM bindings for RuvLLM - browser-compatible LLM inference runtime with WebGPU acceleration
Attention mechanisms for ruvector - geometric, graph, and sparse attention
Node.js bindings for ruvector-attention
Training pipeline for WiFi-DensePose pose estimation
High-performance WebAssembly attention mechanisms: Multi-Head, Flash, Hyperbolic, MoE, CGT Sheaf Attention with GPU acceleration for transformers and LLMs
WiFi CSI signal processing for DensePose estimation
RuVector v2.0.4 integration layer — ADR-017 signal processing and MAT ruvector integrations
Unified graph transformer with proof-gated mutation substrate — 8 verified modules for physics, biological, manifold, temporal, and economic graph intelligence
CNN feature extraction for image embeddings with SIMD acceleration
OSpipe: RuVector-enhanced personal AI memory system integrating with Screenpipe
Hyperbolic (Poincare ball) embeddings with HNSW integration for hierarchy-aware vector search, enabling efficient similarity search in non-Euclidean spaces for taxonomies, ontologies, and hierarchical data
Unified WebAssembly bindings for 18+ attention mechanisms: Neural, DAG, Graph, and Mamba SSM