aicoolies logo

pgvector

Vector similarity search for PostgreSQL

Share
open-sourceOpen Source
Visit Website →

pgvector is an open-source PostgreSQL extension with 14K+ GitHub stars adding vector similarity search to your existing Postgres database. Store embeddings alongside relational data, perform exact and approximate nearest neighbor search using L2, inner product, cosine, and L1 metrics. Supports HNSW and IVFFlat indexes for fast similarity queries at scale. Eliminates the need for a separate vector database by bringing vector capabilities into existing PostgreSQL infrastructure.

pgvector adds vector similarity search to PostgreSQL. With 14K+ stars, it is the default choice for teams wanting vector search without adding a separate database.

Store embeddings as a native column type alongside relational data. Combine SQL filters with vector similarity search in a single query.

HNSW indexes for high-recall approximate search, IVFFlat for faster builds. L2, inner product, cosine, and L1 distance metrics.

Works with Supabase, Neon, AWS RDS, Google Cloud SQL, and self-hosted. Integrates with LangChain, LlamaIndex, and all AI frameworks supporting PostgreSQL.

Pricing

Free and open-source

Platforms

PostgreSQL extension

Categories

PostgreSQL ToolsVector DatabasesDatabases & ORMs

Tags

Multi-ModelAgenticBYOK

Use Cases

Database Schema DesignData Engineering

Alternatives

pg_textsearch

BM25 full-text search extension for PostgreSQL

pg_textsearch is a PostgreSQL extension from Timescale that adds BM25 relevance-ranked full-text search directly inside Postgres. Using the same ranking algorithm as Elasticsearch and Lucene, it provides search-engine quality results without requiring a separate search cluster — particularly valuable for developers building RAG pipelines on PostgreSQL who want semantic-quality ranking alongside pgvector.

open-sourceOpen Source
Tembo logo

Tembo

Managed Postgres platform with 200+ extensions as pre-built stacks

Tembo is a managed PostgreSQL platform that packages 200+ Postgres extensions into purpose-built stacks for specific workloads. Stacks include OLAP analytics, vector search, message queues, geospatial, and machine learning, turning PostgreSQL into a specialized database for each use case. Eliminates the need for separate Redis, Elasticsearch, or Kafka instances alongside Postgres.

freemiumOpen Source
Marqo logo

Marqo

Embedding-first search and discovery engine for AI-powered product experiences.

Marqo is an open-source tensor search engine that combines embedding generation and vector search in a single API, removing the need to manage separate embedding pipelines and vector databases. Built for product discovery and multi-modal search, it lets teams index text, images, and structured data together, returning ranked results based on semantic similarity rather than keyword overlap.

freemium

Related Tools

Supabase MCP

MCP server for connecting AI assistants to Supabase projects

Supabase MCP is Supabase's Apache-2.0 server for connecting AI assistants to Supabase projects. It can expose database, configuration, and project-management workflows to MCP clients such as Cursor, Claude, and Windsurf, while the official docs emphasize permission and security review before production use, SQL changes, or high-privilege database access.

open-sourceOpen SourceTelemetry
Deep Lake logo

Deep Lake

AI data runtime for multimodal datasets and vector search

Deep Lake is an open-source AI data runtime from Activeloop for storing, versioning, and querying multimodal data and embeddings. It fits teams building RAG, training, evaluation, or dataset-heavy agent workflows that need a bridge between vector search, structured metadata, and large image, text, audio, or video collections.

open-sourceOpen Source
SeekDB logo

SeekDB

AI-native state store with hybrid vector and full-text search

SeekDB is an open-source AI-native state store from the OceanBase ecosystem that combines MySQL-compatible data access with hybrid vector and full-text retrieval. It targets agent and AI application teams that need embedded or server deployment, copy-on-write style sandboxes, and searchable state without gluing together several separate storage layers.

open-sourceOpen Source

pgvectorscale

DiskANN-powered vector search extension for PostgreSQL

pgvectorscale is an open-source PostgreSQL extension from Timescale that complements pgvector with DiskANN-based approximate vector search. It is useful for teams that want faster embedding retrieval while keeping vectors, filters, and application data inside the Postgres ecosystem instead of adopting a separate hosted vector database.

open-sourceOpen Source
Ardent logo

Ardent

Database branching for coding agents

Ardent is a Postgres database branching platform built for coding-agent workflows. It creates isolated database copies in seconds so Claude Code, Codex, Cursor, or human developers can test migrations, clean data, reproduce bugs, and run risky experiments without touching production. The strongest fit is teams already using Postgres who need agent-safe dev/test databases rather than another generic serverless database.

freemium
Vald logo

Vald

Cloud-native distributed vector search engine built for Kubernetes with automatic indexing and horizontal scaling.

Vald is a highly scalable distributed approximate nearest neighbor (ANN) vector search engine designed for cloud-native, Kubernetes-based architectures. Maintained by LY Corporation and listed in the CNCF Landscape, it uses the NGT algorithm (developed at Yahoo Japan), supports automatic incremental index backup, and handles billion-scale datasets across loosely coupled microservice components that scale horizontally via Helm.

open-sourceOpen Source

Comparisons

pgvectorscale vs pgvector — Scaling PostgreSQL Vector Search

pgvectorscale and pgvector are not simple substitutes: pgvector is the standard PostgreSQL vector extension, while pgvectorscale builds on pgvector data with Timescale's StreamingDiskANN and filtered-search focus. For teams already committed to Postgres, the real choice is whether pgvector alone is enough or whether production RAG workloads need an additional scaling layer. This comparison separates default adoption, index performance, managed-Postgres constraints, and operational risk.

pgvectorscalepgvector

pgvector vs Pinecone — Postgres-Native RAG or Managed Vector Database?

pgvector and Pinecone answer the same RAG question from opposite directions: should your vectors live inside Postgres with the rest of your application data, or should you use a managed vector database built for search at scale? pgvector is simpler when your data model already belongs in Postgres. Pinecone is the stronger default when vector search becomes its own production workload with scaling, latency, and operations requirements.

pgvectorPinecone

VectorChord vs pgvector — Postgres Vector Search at Two Different Scales

VectorChord and pgvector are both Postgres extensions for vector search, but they answer different questions. pgvector is the simple, ubiquitous choice for adding vectors to Postgres at small to medium scale. VectorChord is the engineered answer for teams that need pgvector-style operations at billion-vector scale — the spiritual successor that picks up where pgvector hits its limits.

VectorChordpgvector