pgvector
Vector search inside the Postgres you already run — zero new infrastructure.
94
sovereigntypgvector is an open-source extension (PostgreSQL license) that adds vector similarity search to PostgreSQL itself. If your app already has Postgres, this is the no-new-moving-parts answer: embeddings live next to your relational data, joins and filters are just SQL, and every major managed Postgres (RDS, Cloud SQL, Azure, Supabase, Neon) supports it. Recent releases added parallel HNSW index builds, iterative scans for filtered queries, and halfvec quantization — it now handles serious workloads, not just prototypes.
OPEN SOURCEPostgreSQLSELF-HOSTLOCAL-FIRST
LicensePostgreSQL
PricingFree — an extension of PostgreSQL; runs wherever your Postgres runs
Open sourceYes
Self-hostableYes
Local-first dataYes
What it does well
- +No new database to operate — it's your existing Postgres
- +Vectors join directly with relational data in SQL
- +Supported by every major managed Postgres provider
- +HNSW indexes, filtered iterative scans, quantization
Where it falls short
- −Very large collections (hundreds of millions of vectors) favor a dedicated engine
- −Tuning happens in Postgres terms — indexes, memory, vacuum
pgvector as an alternative to
Where pgvector shows up in our comparisons, and how it ranked.
pgvector head-to-head
Straight comparisons against the tools people weigh it against.