---
title: "VectorChord"
type: "tool"
slug: "supervc-stack-vectorchord"
canonical_url: "https://www.graphcanon.com/tools/supervc-stack-vectorchord"
github_url: "https://github.com/supervc-stack/VectorChord"
homepage_url: "https://docs.vectorchord.ai/vectorchord/getting-started/overview.html"
stars: 1731
forks: 70
primary_language: "Rust"
license: "Other"
categories: ["vector-databases"]
tags: ["scalable", "affordable-vector-storage", "postgresql-extension", "disk-friendly", "vector-search", "rabitq-compression"]
updated_at: "2026-07-07T20:09:39.940068+00:00"
---

# VectorChord

> Scalable, fast, and disk-friendly vector search in Postgres

VectorChord is a PostgreSQL extension for scalable, high-performance, and cost-effective vector search. It supports RaBitQ compression and autonomous reranking to efficiently store vectors while maintaining high-quality search.

## Facts

- Repository: https://github.com/supervc-stack/VectorChord
- Homepage: https://docs.vectorchord.ai/vectorchord/getting-started/overview.html
- Stars: 1,731 · Forks: 70 · Open issues: 17 · Watchers: 16
- Primary language: Rust
- License: Other
- Last pushed: 2026-06-25T06:33:25+00:00

## Categories

- [Vector Databases](/categories/vector-databases.md)

## Tags

scalable, affordable-vector-storage, postgresql-extension, disk-friendly, vector-search, rabitq-compression

## Related tools

- [meilisearch](/tools/meilisearch-meilisearch.md) - Meilisearch is a lightning-fast search engine API that brings AI-powered hybrid search to your sites and applications. (★ 58,449)
- [milvus](/tools/milvus-io-milvus.md) - High-performance vector database built for scalable vector ANN search (★ 45,121)
- [qdrant](/tools/qdrant-qdrant.md) - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. (★ 33,008)
- [chroma](/tools/chroma-core-chroma.md) - Data infrastructure for AI (★ 28,721)
- [weaviate](/tools/weaviate-weaviate.md) - Open-source vector database for semantic search (★ 16,534)
- [doris](/tools/apache-doris.md) - Apache Doris is a real-time analytics and hybrid search database for AI agents. (★ 15,587)
- [self-hosted-ai-starter-kit](/tools/n8n-io-self-hosted-ai-starter-kit.md) - A self-hosted AI environment setup for local development (★ 15,031)
- [zvec](/tools/alibaba-zvec.md) - A lightweight, lightning-fast, in-process vector database (★ 13,974)

## README (excerpt)

```text
<div align="center">

# VectorChord

**Ready for the Billion-Scale Era. Host 100M vectors on a single i4i.xlarge ($247/mo) and [scale seamlessly to 1B+](https://blog.vectorchord.ai/scaling-vector-search-to-1-billion-on-postgresql).**

[Official Site][official-site-link] · [Blog][blog-link] · [Docs][docs-link] · [Feedback][github-issues-link] · [Contact Us][email-link]

[![][github-release-shield]][github-release-link]
[![][docker-release-shield]][docker-release-link]
[![][docker-pulls-shield]][docker-pulls-link]
[![][ghcr-release-shield]][ghcr-release-link]
[![][github-downloads-shield]][github-downloads-link]
[![][discord-shield]][discord-link]
[![][X-shield]][X-link]
[![][deepwiki-shield]][deepwiki-link]
[![][license-1-shield]][license-1-link]
[![][license-2-shield]][license-2-link]

</div>

VectorChord (vchord) is a PostgreSQL extension engineered for scalable, high-performance, and cost-effective vector search.

To efficiently store vectors while preserving search quality, VectorChord applies RaBitQ[^1] compression together with autonomous reranking. With VectorChord, you can store 400,000 vectors for just $1, enabling significant savings: 6x more vectors compared to Pinecone's optimized storage and 26x more than pgvector/pgvecto.rs for the same price.

[^1]: Gao, Jianyang, and Cheng Long. "RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search." Proceedings of the ACM on Management of Data 2.3 (2024): 1-27.

![][image-compare]

## Features

VectorChord introduces remarkable enhancements over pgvecto.rs and pgvector:

**💰 Affordable Vector Search**: Host 100M × 768-dimensional vectors → AWS i4i.xlarge ($247/month)[^2], host 1B × 96-dimensional vectors → i7ie.6xlarge ($2246/month)[^3], helping you keep infrastructure costs down while maintaining competitive search quality.

[^2]: Please check out our [blog post](https://blog.vectorchord.ai/vectorchord-store-400k-vectors-for-1-in-postgresql) for more details.
[^3]: Please check out our [blog post](https://blog.vectorchord.ai/scaling-vector-search-to-1-billion-on-postgresql) for more details.

**⚡ Accelerated Index Build**: Index 100 million vectors in just 20 minutes. Powered by hierarchical K-means and highly optimized disk operations, VectorChord eliminates the bottleneck of vector indexing on a single machine with limited hardware resources.

[^4]: Please check out our [blog post](https://blog.vectorchord.ai/how-we-made-100m-vector-indexing-in-20-minutes-possible-on-postgresql#heading-hierarchical-k-means) for more technique details and [document](https://docs.vectorchord.ai/vectorchord/usage/partitioning-tuning.html#hierarchical-k-means) for usages.

**📈 Smoothly Scale Up**: Scale with confidence as your data grows. Through dimensionality reduction and sampling[^5], VectorChord effectively controls memory growth, enabling 1B-vector indexes to be built on machines with 128GB of memory in practice.

[^5]: Please check out our [blog post](https://blog.vectorchord.ai/how-we-made-100m-vector-indexing-in-20-minutes-possible-on-postgresql#heading-dimensionality-reduction) for more technique details and [document](https://docs.vectorchord.ai/vectorchord/usage/partitioning-tuning.html#reduce-sampling-factor) for usages.

**🔌 Seamless Integration**: Fully compatible with pgvector data types and syntax while providing optimal defaults out of the box - no complex parameter tuning needed. Just drop in VectorChord for enhanced experience.

**💾 Efficient Storage with Low-Bit Data type**: Drastically reduce storage costs with our [native 4-bit (RaBitQ4) and 8-bit (RaBitQ8) vector types](https://docs.vectorchord.ai/vectorchord/usage/quantization-types.html). Achieve massive space savings without compromising search quality—RaBitQ8 maintains high precision with <1% recall loss.

## Quick Start

For new users, we recommend using the Docker image to get started quickly. If you do not prefer Docker, please read [installation gui
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/supervc-stack-vectorchord`](/api/graphcanon/tools/supervc-stack-vectorchord)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_