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.

VectorChord
57
Established
pgvecto.rs
41
Emerging
Maintenance 17/25
Adoption 10/25
Maturity 16/25
Community 14/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 15/25
Stars: 1,595
Forks: 56
Downloads:
Commits (30d): 6
Language: Rust
License:
Stars: 2,158
Forks: 83
Downloads:
Commits (30d): 0
Language: Rust
License: Apache-2.0
No Package No Dependents
Stale 6m No Package No Dependents

About VectorChord

tensorchord/VectorChord

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

This project helps you manage and search through extremely large collections of digital information, like millions of product descriptions or scientific papers, by converting them into 'vector embeddings'. It takes these high-dimensional vectors as input and lets you quickly find the most similar items, outputting relevant results efficiently. This is ideal for AI application developers, data engineers, or ML operations specialists who need to power recommendation engines, semantic search, or large language model (LLM) applications.

AI-application-development semantic-search recommendation-engines LLM-backend data-infrastructure

About pgvecto.rs

tensorchord/pgvecto.rs

Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database.

This is a Postgres extension that helps you find similar data points in your database by comparing their 'vector' representations. You input data along with its numerical vector, and it outputs the most similar items based on different distance calculations. Data scientists, machine learning engineers, and developers building AI-powered applications that rely on similarity searches would use this.

vector-database similarity-search recommendation-systems semantic-search data-retrieval

Related comparisons

Scores updated daily from GitHub, PyPI, and npm data. How scores work