Vector database

Pinecone for Postgres: one pgvector column, three engines

⚡ In-Memory Vector Search Engine & HNSW ANN Graph in Java 21 Loom. Sub-millisecond KNN retrieval, 8-bit scalar quantization (SQ8), 16,000+ QPS.

Billion-scale embedded vector database built entirely on Parquet and Arrow.

A full AI search engine, built into Postgres.

Face search engine: 100% recall at 96x less memory than HNSW. Register photos, identify people from camera/video/images. AVX-512 + Rust. No GPU needed.

A local-first CLI that makes your Obsidian vault (or Markdown Notes) searchable and AI-Agents queryable with semantic search and hidden connections.

Business2Vector AI 2026: Smart Embedding Engine for Strategic Enterprise Vectorization

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

Semantic code search and context engine for AI coding agents.

PostgreSQL extension for generating text embeddings in Rust with pgrx, Candle, and optional pgvector support.

A multi-tenant vector database focused on extreme RAM efficiency. Lightweight, scalable, and optimized for high-density deployments.

Python SDK for vector search, semantic search, RAG, embeddings, and AI agents on Oracle AI Database

A vector index built on TurboQuant, written in Rust with Python bindings

TalaDB - An open-source embedded vector and document database for building local-first AI applications.

A cross-platform vector database, which can be integrated into existing databases as a plugin.

Vector DB version control, 100% Rust, Mac, Linux, Windows compatible

VectorRAG.Net is a .NET-native high-performance vector database library for semantic search and RAG (Retrieval-Augmented Generation). Core search is based on Random Hyperplane LSH candidate generation with exact rerank by dot/cosine.

High-performance vector search for PostgreSQL

[H] HyperspaceDB is a high-performance, vector database. It features 1-bit quantization, async replication, and native support for hierarchical datasets (Lorentz, Poincaré ball & Hybrid models).

Endee.io – A high-performance vector database, designed to handle up to 1B vectors on a single node, delivering significant performance gains through optimized indexing and execution. Also available in the cloud at https://endee.io and under the Endee Enterprise license. Free 30-day evaluation: https://docs.endee.io/v2/quick-start/enterprise

High-performance on-device vector search engine for Expo & React Native. Powered by C++ JSI and USearch (HNSW) for sub-millisecond similarity matching.