---
id: "entity-pgvector"
type: "entity"
entityType: "tool"
canonicalName: "pgvector"
aliases: []
source_timestamps: ["00:15:12"]
tags: ["database-extension", "vector-search"]
related: ["entity-postgresql", "concept-semantic-search"]
url: "https://github.com/pgvector/pgvector"
sources: ["s22-saas-replacement"]
sourceVaultSlug: "s22-saas-replacement"
originDay: 22
---
# pgvector

## Profile

An open-source vector similarity search extension for [[entity-postgresql]]. It adds a `vector` column type and similarity operators (cosine distance, inner product, L2) so the database can perform native nearest-neighbor search against high-dimensional embeddings.

## Role in This Source

pgvector is the technology that makes traditional Postgres natively readable by AI agents — i.e. it transforms a generic RDBMS into a viable [[concept-agent-web]] memory store. Without pgvector, the [[concept-open-brain-d22]] would either need a separate vector DB (more moving parts) or fall back on keyword search (loses [[concept-semantic-search]]).

Referenced operationally in [[framework-open-brain-architecture]] (Store step) and [[action-build-postgres-db]].