kitio.aiAdded Oct 28, 2026
pgvector
FreeOpen-source vector similarity search extension for Postgres
What is pgvector?
pgvector is an open-source Postgres extension that adds a vector column type and similarity search, letting you store embeddings next to your regular data. It is supported by most managed Postgres services, so many teams use it instead of a separate vector database.
pgvector supports exact and approximate nearest-neighbor search with HNSW and IVFFlat indexes, plus cosine, inner product and L2 distance. Queries use normal SQL, so joins, filters and transactions work as usual.
It is free under the PostgreSQL license and available as a built-in extension on Supabase, Neon, Amazon RDS, Google Cloud SQL, Azure Database for PostgreSQL and other hosts.
Features
- Vector column type
- HNSW and IVFFlat indexes
- Multiple distance metrics
- Plain SQL queries
- Wide cloud support
Tags
Releases
+ Submit new release- Listed
pgvector was added to the directory.
Organization
pgvector contributors
Listed by kitio.ai · unverified owner
Pricing
- Pricing model
- Free
- Paid options from
- 100% free
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top pgvector alternatives
View allModels & APIs
Open-source library for similarity search over dense vectors
Models & APIs
Open-source engine for search, recommendation and RAG at scale
Models & APIs
The main hub for open models, datasets and AI demo apps
Models & APIs
Run open models locally with one command, plus optional cloud models
If you liked pgvector
Real-time SQL database for AI apps, with vectors and a plain-English analyst
Free trialData & analyticsMade in United StatesHigh-throughput open-source engine for serving LLMs in production
FreeModels & APIsMade in United StatesRun and deploy open-source AI models through a simple API
PaidModels & APIsMade in United States
Pros and cons
Pros
- Uses your existing database
- Free and widely supported
- Full SQL power
Cons
- Slower than specialized engines at scale
- Index builds use memory
- Tuning needs Postgres skills
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is pgvector?
pgvector is an open-source Postgres extension that adds a vector column type and similarity search, letting you store embeddings next to your regular data. It is supported by most managed Postgres services, so many teams use it instead of a separate vector database.
How much does pgvector cost?
pgvector is 100% free.
Is there a free version of pgvector?
Yes. pgvector is completely free to use.
What are the main features of pgvector?
Vector column type, HNSW and IVFFlat indexes, Multiple distance metrics, Plain SQL queries, Wide cloud support.
Who makes pgvector?
pgvector is made by pgvector contributors.
What are the best alternatives to pgvector?
Popular alternatives include Faiss, Vespa, Hugging Face.