Show HN: EdgeVec – Sub-millisecond vector search in the browser (Rust/WASM) https://bit.ly/48YXwdY

Show HN: EdgeVec – Sub-millisecond vector search in the browser (Rust/WASM) Hi HN, I built EdgeVec, a vector database that runs entirely in the browser. It implements HNSW (Hierarchical Navigable Small World) graphs for approximate nearest neighbor search. Performance: - Sub-millisecond search at 100k vectors (768 dimensions, k=10) - 148 KB gzipped bundle - 3.6x memory reduction with scalar quantization Use cases: browser extensions with semantic search, local-first apps, privacy-preserving RAG. Technical: Written in Rust, compiled to WASM. Uses AVX2 SIMD on native, simd128 on WASM. IndexedDB for browser persistence. npm: https://bit.ly/4ptTr8q GitHub: https://bit.ly/49efj0T This is an alpha release. Main limitations: build time not optimized, no delete operations yet. Would love feedback from the community! https://bit.ly/49efj0T December 12, 2025 at 11:39PM