Vector Databases
Vector databases purpose-built for AI applications — store, index, and search high-dimensional embeddings at scale. These are the retrieval backbone of RAG pipelines, semantic search, and long-term agent memory. Available as managed cloud services or open-source self-hosted deployments.
LanceDB
Stores and searches multimodal vectors in an embedded database built on the Lance columnar format, running in-process o…
LightRAG
Builds a graph-based retrieval index over documents so agents can answer questions spanning many sources, served throug…
Typesense
Runs typo-tolerant search with built-in vector, hybrid, and semantic modes over a REST API, self-hosted or on Typesense…
Algolia
Hosted search and discovery API with typo tolerance, faceting, and vector search, callable directly for agent retrieval…
ChromaDB
Open-source embedding database for local and cloud AI apps. Simple API for storing, querying, and filtering embeddings.…
Codebase Memory MCP
Indexes repositories into a persistent tree-sitter knowledge graph of functions, classes, call chains, and HTTP routes,…
Cognee
Builds queryable memory for agents by turning documents and conversations into a knowledge graph plus vector store, sel…
Elasticsearch MCP Server
Official Elastic MCP server letting agents query Elasticsearch indices, run search and aggregations, and inspect mappin…
Milvus
High-performance open-source vector database with REST API, gRPC, and an official MCP server. Stores billions of vector…
PageIndex
Indexes long documents as a reasoning-based hierarchical tree so agents retrieve by navigating structure instead of emb…
Pinecone
Fully managed vector database for AI applications. Store and search billions of high-dimensional embeddings with low la…
Qdrant
High-performance open-source vector database. Supports dense, sparse, and multi-vector search. On-premise or cloud. Rus…
Supabase MCP
Official Supabase MCP server. Lets AI agents manage Postgres databases, run queries, handle migrations, store pgvector…
turbopuffer
Gives search and RAG backends a serverless vector and BM25 full-text search database built on object storage, queried o…
turbovec
Indexes and searches embeddings with 2- to 4-bit TurboQuant compression in a Rust library with Python bindings, for loc…
Weaviate
Stores objects and vectors together, combining semantic search with structured filtering for scalable, cloud-native AI…
Zvec
Embeds an in-process vector database into applications for dense, sparse, full-text, and hybrid search with durable loc…