{
  "slug": "pgvector",
  "name": "pgvector",
  "url": "https://github.com/pgvector/pgvector",
  "cat": "search",
  "group": "back",
  "tagline": "Vector search inside Postgres",
  "price": "pgvector itself is free and open source. On Supabase it is a one-click extension included at every tier: Free plan 500MB database, 50K MAU, 2 active projects; Pro from $25/mo.",
  "tier": "mixed",
  "pick": false,
  "what": "A Postgres extension adding a <code>vector</code> column type with HNSW and IVFFlat indexes, L2, cosine, inner-product, L1, Hamming and Jaccard distance, and up to 16,000 dimensions. Supabase enables it in one click, so embeddings live in the same database and the same transaction as your app rows.",
  "why": "One database instead of two. You can join a similarity search against your users table and enforce row-level security on retrieval — impossible with a separate vector service.",
  "warn": "HNSW builds are memory-hungry and slow on small instances, and a missing index silently degrades to a full scan. Past a few million vectors a dedicated vector DB wins.",
  "install": "create extension vector;",
  "category": {
    "key": "search",
    "name": "Search, vector & RAG",
    "desc": "Keyword search, vector stores, and web-search APIs for agents — three different things.",
    "group": "back",
    "groupName": "Give it a backend"
  },
  "freshness": null,
  "health": {
    "ok": true,
    "status_code": 200,
    "final_url": null,
    "checked_at": "2026-08-18T18:09:22.039+00:00"
  },
  "corrected_at": null,
  "upstream_changed_at": null
}