Retrieval-Augmented Generation (RAG) & Knowledge

GraphQL-native vector search engine.

Scalable cloud-native vector database.

Low-latency graph and vector hybrid retrieval database in Go with Neo4j and Qdrant-compatible drivers.

Most popular open-source embedding database.

High-performance vector search engine in Rust.

Similarity search and clustering library for dense vectors with CPU and GPU implementations.

Serverless vector DB optimized for multimodal data.

AI + Data platform with hybrid search (vector + keyword) and real-time indexing at scale. Battle-tested serving billions of queries daily.

PostgreSQL extension for vector similarity search.

PostgreSQL extension for scalable vector search with DiskANN algorithm. Complements pgvector with significantly faster search and higher recall at large scale. PostgreSQL licensed.

Scalable, fast, and disk-friendly vector search in Postgres. Successor to pgvecto.rs with production-grade performance and efficient storage. AGPL-3.0 licensed.

Cloud-native search engine for observability. Open-source alternative to Datadog, Elasticsearch, Loki, and Tempo with native vector search support.

Full-text search engine library inspired by Apache Lucene and written in Rust. Powers Quickwit and other production search systems.

Easy to use open source fast database for search. Good alternative to Elasticsearch with SQL-like interface and vector search capabilities.

Open-source distributed and RESTful search and analytics suite with native vector search. Enterprise-grade fork of Elasticsearch with k-NN plugin for semantic search at scale.

Multimodal vector search for text, image, and structured data. End-to-end indexing and search with built-in embedding models. Apache 2.0 licensed.

Highly scalable distributed vector search engine. Cloud-native architecture with automatic indexing, horizontal scaling, and multiple ANN algorithm support. Apache 2.0 licensed.

Header-only C++ library for fast approximate nearest neighbors with Python bindings. Supports CRUD operations and concurrent read/write - unique among ANN libraries. Powers many production vector databases. Apache 2.0 licensed.

Rust-native high-performance vector index with Python bindings optimized for fast ANN search and SIMD acceleration on modern CPUs. MIT licensed.

A vector search SQLite extension that runs anywhere. Extremely small, "fast enough" vector search written in pure C with no dependencies. Perfect for embedded and edge deployments. MIT/Apache-2.0 dual licensed.

Lightweight, lightning-fast, in-process vector database from Alibaba. Built on Proxima (Alibaba's battle-tested vector search engine) for production-grade, low-latency similarity search. Apache 2.0 licensed.

Lightning-fast search engine API with AI-powered hybrid search. Features typo-tolerant full-text search combined with HNSW-based vector search for semantic retrieval. MIT licensed.

Open source alternative to Algolia + Pinecone. Fast, typo-tolerant, in-memory fuzzy search engine with native vector search capabilities. GPL-3.0 licensed.

Distributed search and analytics engine with native k-NN vector search, hybrid search, and dense vector indexing. Industry-standard for full-text search now with powerful semantic search capabilities. AGPL-3.0/Elastic-2.0 dual licensed.