Skip to content
AgentsIndex

pgvector

Open-source Postgres extension that stores vectors beside relational data and runs similarity search in SQL.

pgvector is an open-source PostgreSQL extension that adds vector column types and exact or approximate nearest neighbor search with HNSW and IVFFlat indexes. Embeddings live in the same database as the rest of an application's data and are queried with ordinary SQL.

Best for
Developers who want vector search inside Postgres without adding a separate database.
GitHub stars
23.3k

What we checked

Pages last read
Facts checked
1 fact

From 1 source, read 30 October 2026

AI answers
Too few read

58 buyer-question answers read, November 2026

At a glance

Tags
Freemium, Open source, Self-hosted

Code

Last push
8 October 2026

For developers

Works with
Docker, Homebrew, PGXN, APT, Yum, pkg and 24 more

pgvector in our research

All research

Study

AI Tool Pricing Index, November 2026

Pricing

Free only

29 of the 361 tools we checked are free with no paid plan.

Edition price, checked 12 November 2026.

Pricing pages of the AI tools, November 2026 editionas of n = 361 tools checked

What it actually is

pgvector is a Postgres extension (C, built with the standard Postgres extension build system) that adds a vector column type plus supporting index types (HNSW, IVFFlat) and distance operators (L2, inner product, cosine, L1, and — for binary vectors — Hamming and Jaccard). It's maintained by Andrew Kane (creator of many similar 'ann' extensions across languages) as a single-purpose extension, not a company or hosted product. Everything runs inside your existing Postgres instance: same backups, same replication, same transactions, same JOINs against your relational data.

Technical capabilities, verified against the current release (v0.8.6)

Vector storage: 4 * dimensions + 8 bytes per vector, up to 2,000 dimensions for indexed vector columns, 4,000 for halfvec (half-precision), and 64,000 for binary-quantized bit vectors; raw (unindexed) vector columns can go up to 16,000 dimensions. Supports exact search out of the box and two approximate index types (HNSW and IVFFlat), plus binary quantization, sparse vectors, iterative index scans (to recover recall lost to post-filtering), and partial/partitioned indexing for multi-tenant isolation. Requires Postgres 13+; official Docker images are published for Postgres 13 through 18. Client libraries exist for roughly 30 languages, maintained in separate pgvector/pgvector-<lang> repos.

Maturity and maintenance

Created in April 2021 and actively maintained: the latest tag is v0.8.6 (29 July 2026), with bug-fix PRs merged as recently as 4 August 2026 (a race condition between HNSW insert and vacuum), and commits as recent as 15 August 2026. Release cadence has been roughly monthly through 2026 (0.8.2 through 0.8.6, plus an 0.8.7 unreleased branch already in the changelog). No security advisories are filed against the repo, and no entries appear in the OSV.dev vulnerability database. One caveat: contribution is heavily concentrated — Andrew Kane accounts for 1,915 of the commits in the top-10 contributor list against 18 for the next-most-active contributor — so this is a single-maintainer project in practice, even though it's widely deployed and gets outside code review from contributors at AWS and other Postgres vendors on individual PRs.

License

The PostgreSQL License — a permissive, OSI-approved license structurally similar to MIT/BSD (no copyleft, no field-of-use restriction). GitHub's own license detector reports it as "Other / NOASSERTION" because the license text is PostgreSQL's own non-templated wording rather than a byte-for-byte match to a known template, not because the terms are unusual or restrictive — the actual LICENSE file text is standard permissive language used by PostgreSQL itself since the 1990s.

Where it stops being the right tool

Independent community reporting (via Qdrant's own comparison post, so read as an interested party) and pgvector's own README agree on the shape of the ceiling: index build time and recall both degrade as the HNSW graph grows past what fits in maintenance_work_mem, and the graph needs to fit in memory for good query performance. Using the README's own storage formula, 10 million vectors at a common embedding size (1536 dimensions, e.g. OpenAI's text-embedding-3-small) works out to roughly 61.5 GB of raw vector storage before HNSW graph overhead — more RAM than most single Postgres instances carry by default. Timescale's Postgres extension pgvectorscale (a separate, third-party project, not part of pgvector itself) adds a disk-based DiskANN index aimed specifically at this gap; Timescale's own benchmark (their product, their numbers) claims 16x higher throughput and 28x lower p95 latency than Pinecone's storage-optimized tier at 50M vectors — useful context on the ceiling, but a vendor benchmark of their own extension, not independent.

Where it's actually deployed

pgvector ships as an installable/preinstalled extension on Amazon RDS and Aurora PostgreSQL, Neon, Supabase, Google Cloud SQL for PostgreSQL, and Azure Database for PostgreSQL, among others — confirmed directly on AWS's and Neon's own docs. Its own README declines to maintain a hosted-provider list and instead points to a community-tracked GitHub issue, which is a reasonable choice for a project this widely adopted but means you should verify support and version on your specific provider before assuming it's current.

pgvector price and terms

Terms

Free plan
YesYesThe published license grants use, copying, modification, and distribution without fee

Where these prices come from

github.com/pgvector/pgvector/blob/master/LICENSE, checked

All plans and limits

PlanPriceMain limits
pgvectorFreeNone stated

Read from github.com/pgvector/pgvector/blob/master/LICENSE.

What we checked on pgvector

What it costs to startNo

What the price counts

The no-fee license establishes a free project rather than a paid seat or usage meter.

Permission to use, copy, modify, and distribute this software and its documentation for any purpose, without fee, and without a written agreement is…

github.com/pgvector/pgvector/blob/maste…Checked

Questions about pgvector

How much does pgvector cost?
pgvector is free to use. From github.com/pgvector/pgvector/blob/master/LICENSE, checked 12 November 2026.
Does pgvector have an API or an MCP server?
pgvector has an API.
Is pgvector open source, and can you host it yourself?
pgvector is open source. You can host pgvector yourself.
What have we checked on pgvector?
1 fact, under one heading: What it costs to start.
How do we check pgvector?
We hold 1 fact on pgvector, quoted from 1 page. Facts last checked 30 October 2026. Price last checked 12 November 2026. Last change found 21 March 2026.

How we check every listing

Sources and changes

Last changed

Repository

Stars
23,326
Last push
8 October 2026

pgvector price history

We have read the price once so far, on 12 November 2026: free.

PricePlanFirst seenLast seenReadingsSource
Free12 November 202612 November 20261Pricing page, read 12 November 2026

From our research on 12 November 2026. A date is when we read the page, not when the price changed.

Similar in Agent tools and integrations

See all in Agent tools and integrations

Is pgvector yours?

Free, and the page then carries the verified owner mark. Claim this listing

Report an error if a fact is wrong.