Databases for Vector search

Open-source retrieval database for AI apps, from embedded Python to serverless Chroma Cloud.

Cloud-native, distributed open-source vector database built for billions of vectors.

Meta's C++/Python library for fast dense-vector similarity search and clustering, CPU and GPU.

The standard Postgres extension for vector similarity search with HNSW and IVFFlat indexes.

Rust vector search engine with rich payload filtering, quantization and a managed cloud.

Open-source AI-native vector database with hybrid search, modules for embeddings and multi-tenancy.

Dependency-free SQLite extension for vector search that runs anywhere SQLite does, including WASM.

Embedded, serverless retrieval database on the Lance columnar format for multimodal AI data.

Serverless vector and full-text search on object storage, priced for billions of documents.

Single-header C++ HNSW library with SIMD distance kernels and bindings for a dozen languages.

Google Cloud's managed ANN service built on ScaNN, now part of Gemini Enterprise Agent Platform.

Header-only C++ HNSW library with Python bindings, from the authors of the HNSW algorithm.

Fully managed serverless vector database with built-in embedding, reranking and assistants.

Spotify's memory-mapped random-projection-tree ANN library; stable but no longer evolving.

End-to-end tensor search engine that embeds text and images for you, built on Vespa.

AI-native C++ database for hybrid search over dense, sparse, multi-vector (tensor) and full text.

TigerData's Postgres extension adding StreamingDiskANN indexes on top of pgvector.

Disk-friendly Postgres vector extension using IVF + RaBitQ, the successor to pgvecto.rs.

Activeloop's tensor-native data engine for AI: vectors, multimodal data and versioning on object storage.

Enterprise RAG and agent platform with managed hybrid retrieval, reranking and hallucination scoring.

C++ vector database using parallel graph traversal; vendor now focuses on an agent platform.

Google Research's ANN library using anisotropic quantization; the tech behind Vertex AI and AlloyDB vectors.

Postgres vector extension built on USearch HNSW; development has stalled since late 2024.

Kubernetes-native distributed vector search engine built on Yahoo Japan's NGT.

KX's vector database for time-aware AI search, with temporal similarity and hybrid retrieval.

Distributed vector database from DataJaguar that also handles time series and geospatial data.

Vector storage and similarity queries built into S3, trading latency for very low cost at scale.

Globally distributed serverless vector index for Cloudflare Workers and Workers AI.

Fully managed Milvus from its creators, with serverless, dedicated and BYOC deployments.

Lucene-based distributed search and analytics engine for text, vectors, logs and metrics.

Apache-licensed, foundation-governed fork of Elasticsearch for search, vectors and observability.

Hosted search-as-a-service with fast typo-tolerant search, merchandising and AI ranking.

Open-source Postgres backend platform: database, auth, storage, realtime and edge functions in one project.

The original Lucene search server: battle-tested, Apache-governed, now with GPU-accelerated vectors.

The Java search library at the heart of Elasticsearch, OpenSearch and Solr, now with HNSW vectors.

Google's globally consistent, horizontally scaling SQL service with graph, vector and full-text built in.

Microsoft's managed search service for full-text, vector, hybrid and agentic retrieval on Azure.

Developer-friendly Rust search engine with typo tolerance and built-in hybrid semantic search.

ACID document database for .NET and beyond, with auto-indexing, Corax search and multi-master replication.

Serverless Postgres with copy-on-write branching and scale-to-zero, now part of Databricks.

Distributed SQL mixing in-memory rowstore and columnstore for real-time analytics, search and vectors.

Rust multi-model database (documents, graph, vectors, live queries) that runs embedded, in WASM or clustered.

In-memory, typo-tolerant search engine in C++ with vector, hybrid and conversational search.

Open-source backend platform with databases, auth, storage, functions and realtime, self-hosted or cloud.

Reactive TypeScript backend with a transactional document database, server functions and live queries.

Elasticsearch-quality BM25 search and fast aggregations inside Postgres via the pg_search extension.

Big-data serving engine for search, recommendation and RAG with tensors and ML ranking.

Tiny TypeScript full-text, vector and hybrid search engine for browsers, servers and the edge.

Fast SQL-first search database, forked from Sphinx, with columnar storage and vector KNN.

Lisp-built RDF and document knowledge graph with vector store, reasoning and LLM agents.

MongoDB's own multi-cloud DBaaS, bundling search, vector search and stream processing.

Multi-model Java database speaking SQL, Cypher, Gremlin, MongoDB and Redis protocols.

Embedded Datalog database blending relational, graph and vector queries; dormant since 2024.

Open-source backend platform on Postgres with Hasura GraphQL, auth, storage and functions.

Rust graph-vector database on object storage, queried through typed SDKs for AI apps.

Pure-Go full-text, geo and vector indexing library from Couchbase.

Serverless Cassandra-as-a-service with vector search and a JSON Data API, now owned by IBM.

Embeddable multidimensional array storage engine for dense and sparse data on object storage.

Serverless Postgres that makes tenants a first-class primitive, with per-tenant isolation and placement.

Open-source Postgres platform with storage-level copy-on-write branching, scale-to-zero and anonymized clones.

Huawei's distributed enterprise RDBMS built on openGauss, aimed at replacing Oracle in Chinese finance.

Huawei-originated open-source RDBMS forked from PostgreSQL, with in-memory and column engines.

MIT-licensed, MongoDB-compatible document engine built as PostgreSQL extensions, run by the Linux Foundation.

Veteran C++ full-text search server with SphinxQL, still shipping as Sphinx 3.

Microsoft's managed community PostgreSQL, with zone-redundant HA, DiskANN vectors and Citus elastic clusters.

Google's Postgres-compatible service with disaggregated storage, a columnar engine and ScaNN vectors.

Redis Ltd.'s own managed Redis on AWS, Azure and GCP, with Active-Active geo-replication and tiering.

Downloadable Spanner that runs on your own servers, other clouds or a laptop, with Paxos and auto-sharding.

Databricks' serverless Postgres built on Neon tech, with branching and sync to Delta tables in Unity Catalog.

Crunchy Data's developer-friendly managed Postgres across AWS, GCP and Azure, now owned by Snowflake.

Memory-optimized AWS graph engine for fast algorithms, openCypher and vector search over large graphs.

Microsoft's managed MongoDB-compatible service, built on the open-source DocumentDB engine.

Packaged enterprise search and RAG platform built on OpenSearch, with crawlers, connectors and hybrid search.

The in-memory data structure server that became the default cache, now with search, JSON and vectors built in.

The default document database: flexible BSON documents, rich queries and built-in sharding.

Microsoft's flagship RDBMS: T-SQL, columnstore, Always On, and now native vectors and JSON.

Google's app platform: Firestore, Realtime Database and Data Connect, plus auth, functions and hosting.

The default property-graph database, with Cypher, a big ecosystem and a managed cloud.

The enterprise heavyweight: RAC, Data Guard and a converged engine for SQL, JSON, graph and vectors.

Community-led MySQL fork with extra storage engines, built-in Galera and a faster feature cadence.

Masterless wide-column database built for always-on writes across data centers.

Serverless document database with realtime listeners, offline SDKs and a new Enterprise edition.

IBM's enterprise RDBMS for Linux, UNIX, Windows and z/OS, with BLU columnar and pureScale clustering.

Microsoft's globally distributed, multi-API NoSQL and vector database with SLA-backed latency.

Native multi-model database: documents, graphs, search and vectors behind one query language.

SAP's in-memory columnar HTAP database, the mandatory engine under S/4HANA.

MySQL-compatible distributed SQL with a row store for OLTP and a columnar replica for real-time analytics.

Real PostgreSQL compiled to WebAssembly: an embeddable Postgres for browsers, Node, Bun and Deno.

Microsoft's always-current managed SQL Server engine, from free serverless databases to 128 TB Hyperscale.

Apache-licensed distributed SQL that reuses the PostgreSQL query layer on a Raft-replicated storage engine.

AWS's managed Valkey, Redis OSS and Memcached service, provisioned or serverless.

Turso's open-contribution SQLite fork with native vectors, a network server and embedded replicas.

Low-latency graph database using sparse matrices, the maintained successor to RedisGraph.

Memory-first distributed JSON database with SQL++, search, vector indexes and mobile sync.

Open-source distributed SQL from Yandex combining row and column tables, topics and vector search.

Distributed SQL database built on Lucene for real-time analytics over machine, IoT and JSON data.

Performance-focused managed MySQL (Vitess) and Postgres, with NVMe-backed Metal clusters and branching.

AWS's MySQL- and PostgreSQL-compatible engine on a shared, six-way replicated storage layer.

Ground-up Rust rewrite of SQLite with concurrent writes, async I/O, CDC and vector search.

Distributed, horizontally scalable graph database in Go with native GraphQL and DQL.

A multi-threaded, shared-nothing in-memory store that speaks Redis and Memcached on one big box.

Community-maintained continuation of Kùzu: embedded columnar graph database with Cypher.

Alipay-proven distributed SQL with MySQL (and Oracle, in Enterprise) compatibility, HTAP and vector search.

AWS's managed MongoDB-API database on a proprietary, Aurora-style storage layer.

Managed, distributed SQLite with pub/sub, edge functions and CRDT sync to on-device databases.

Multi-model data platform (SQL, objects, globals, vectors) with built-in interoperability, big in healthcare.

Fast on-device object database with built-in HNSW vector search and an optional commercial sync server.

Google Cloud's managed MySQL, PostgreSQL and SQL Server, with an Enterprise Plus tier for fast failover.

Managed SQLite-compatible cloud for database-per-tenant apps, with embedded replicas and offline sync.

Node.js runtime that fuses database, cache, app logic and MQTT/WebSocket messaging in one process.

Embedded JSON document database with SQL++ queries, vector search and sync to Couchbase.

Microsoft Research's .NET cache-store that speaks RESP and scales across cores and storage tiers.

GPU- and vector-accelerated database for real-time spatial, time-series and vector analytics.

MySQL-compatible cloud-native HTAP database on object storage, with vector search and snapshots.

Google Cloud's managed in-memory family: Valkey, Redis, Redis Cluster and Memcached.

Immutable RDF graph database with time travel, git-style branching, SPARQL, JSON-LD and Cypher.

Actian's vectorized columnar analytics database, born from CWI's X100; renamed Analytics Engine in 2026.

A durable, Valkey/Redis-compatible in-memory database on AWS backed by a multi-AZ transaction log.

Baidu's MySQL-compatible distributed HTAP database on RocksDB and Raft, with full-text and vector indexes.

Multi-model database for IoT and observability: time series, full-text, vector and key-value on Parquet.

Oracle's managed MySQL with an in-memory columnar engine for analytics, lakehouse, ML and vector search.

Microsoft's managed Redis built on Redis Enterprise, replacing the retiring Azure Cache for Redis.

Couchbase's managed DBaaS: Couchbase Server clusters plus App Services sync and AI tooling.

Self-driving Oracle Database on Exadata: auto-patching, auto-scaling, and Select AI, on OCI and other clouds.