VectorChord and pgvecto.rs
VectorChord is the successor project that replaces pgvecto.rs, making them direct competitors where users should migrate to the newer option rather than use both.
About VectorChord
tensorchord/VectorChord
Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.
Implements RaBitQ quantization with autonomous reranking to achieve 4-26x better storage efficiency than alternatives, indexing 100M vectors in 20 minutes through hierarchical K-means and optimized disk I/O. Scales to 1B+ vectors via dimensionality reduction and sampling while maintaining memory bounds. Maintains full pgvector API compatibility, allowing drop-in replacement without application changes.
About pgvecto.rs
tensorchord/pgvecto.rs
Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database.
Implements the VBASE indexing method for combined vector search with relational filtering and joins, supports extended vector types (binary, FP16, INT8) and up to 65535 dimensions with runtime SIMD dispatch, and manages indexes separately from PostgreSQL's native storage for optimized performance. Built as a Rust-based PostgreSQL extension using pgrx, it provides three distance metrics (Euclidean, dot product, cosine) through SQL operators for seamless integration with standard queries.
Scores updated daily from GitHub, PyPI, and npm data. How scores work