Alternatives to pgvector

Milvus is an open-source vector database for billion-scale similarity search, hybrid retrieval, and lake-native RAG workloads

Databend is an open-source, cloud-native data warehouse in Rust that runs BI analytics, vector search, full-text search and geospatial on

Open-source RAG engine with built-in ETL, hybrid vector/BM25 search and visual agent orchestration for enterprise AI agents.

Vespa is an open-source AI search platform for hybrid vector, text, and tensor retrieval with machine-learned ranking.

Vespa AI is an open-source AI search platform for hybrid vector, text and structured retrieval with ML ranking in one query pass.

Apache Doris unifies OLAP analytics, full-text search, and vector search in one open-source SQL engine.

Open-source in-process vector database from Alibaba — install one Python package, query millions of vectors in seconds.

AI-native graph database running vector similarity and OpenCypher traversal in one query for GraphRAG pipelines.

Open-source context retrieval layer that syncs your apps and databases so AI agents query live business data in natural language.

MongoDB Atlas stores vector embeddings next to operational data, so RAG apps skip the sync pipeline.

Pinecone is a managed vector database and knowledge engine for RAG, semantic search, and agent retrieval.

Weaviate is an open-source AI database for vector search, hybrid search, and RAG with built-in embeddings and agent memory.

Open-source Microsoft Research RAG that builds a knowledge graph and community summaries from your documents, then queries them in four modes.

LanceDB is an open-source multimodal lakehouse that keeps curation, feature engineering, hybrid search, and training on one Lance table.

Zilliz Cloud: a fully managed vector database on Milvus for billion-scale AI search, RAG, and recommendations.

Apache 2.0 search infrastructure for AI that keeps vectors, indexes and metadata on cheap object storage.

TiDB is a distributed SQL database for AI agents that unifies ACID transactions, HTAP analytics, and native vector search in one engine.

Lance is an open lakehouse format for multimodal AI, pairing a file format, table format, and catalog spec with hybrid vector and full-text search on object

Open-source Python framework that incrementally keeps AI agent context fresh by reprocessing only changed data.

TopK is a unified retrieval engine that runs multi-vector, dense, sparse, regex, and metadata-filtered search in one query, billed per unit of usage.

Open-source wire protocol suite that standardizes LLM, vector, graph, and embedding calls so you swap providers in config, not code

Kronotop is a distributed transactional document database that gives every AI agent or tenant its own namespace with built-in vector search.

Zilliz Cloud Serverless is a managed serverless vector database on Milvus, with auto-scaling compute and tiered storage for GenAI apps.

Free MIT-licensed web admin UI for the Chroma embedding database, built with Next.js

Open-source CLI that turns 18 source types into AI skills and RAG knowledge for 22 AI platforms.

Elasticsearch Labs: free tutorials, notebooks, and reference apps for AI search, vector search, and RAG on Elasticsearch.

Open-source, in-memory text vector database for .NET apps that adds semantic search and RAG without provisioning a vector server.

Xberg is an open-source content intelligence engine that extracts 107 document, web, code, image and audio formats into clean Markdown,

Run LLM inference, embeddings, and ML training directly inside PostgreSQL using SQL functions, or use the Korvus SDK for RAG pipelines.

NodeDB is a universal database engine that unifies vector, graph, document, columnar, key-value, full-text, sparse arrays, and CRDT in one binary over plain