Data, search & knowledge

Vector databases & semantic search

1,175 agents · most starred first

Vector databases & semantic search, page 6 of 12

agent-framework-postgres

PostgreSQL and pgvector integration for Microsoft Agent Framework.

agent-framework-qdrant

Qdrant vector stores for Microsoft Agent Framework.

agent-framework-usearch

Microsoft Agent Framework USearch.

agent-framework-weaviate

Microsoft Agent Framework weaviate.

agent-memory-inspector

Inspect, compare, and evaluate vector retrieval — MRR, Recall@k, and rank diff in one library

agentcraft-db-client

Python SDK for a AgentCraft (Crafted) Vector DB

agentforge-reranker-cohere

Cohere managed-API reranker for AgentForge

agentforge-reranker-mixedbread

Mixedbread AI managed-API reranker for AgentForge

agentforge-reranker-sentence-transformers

SentenceTransformers cross-encoder reranker for AgentForge

agentforge-reranker-voyage

Voyage AI managed-API reranker for AgentForge

agentforge-voyage

Voyage AI embedding provider for AgentForge — voyage-3 / voyage-large / voyage-code

agentvec

Embedded, serverless vector database for mutable AI agent memory — pure Rust, with native TTL, in-place upserts, and incremental HNSW search

agentvectordb

AgentVectorDB (AVDB): The Cognitive Core for Your AI Agents. A lightweight, embeddable vector database for Agentic AI systems, built on LanceDB.

alignllm-case-alignment-package

A package for computing case alignment using embeddings - AlignLLM

alloydb-haystack

An integration of Google Cloud AlloyDB with Haystack for vector search

arcadedb-haystack

An integration of ArcadeDB with Haystack — document storage + HNSW vector search + SQL filtering

basejump-llama-index-embeddings-azure-openai

llama-index embeddings azure openai integration

basejump-llama-index-embeddings-openai

llama-index embeddings openai integration

basejump-llama-index-vector-stores-redis

llama-index vector_stores redis integration

bbm25-haystack

Haystack 2.x In-memory Document Store with Enhanced Efficiency

bestrag

bestrag: Library for storing and searching document embeddings in a Qdrant vector database using hybrid embedding techniques.

cellmetrik

Geometric manipulations on embeddings.

clamp-rag

Git-like version control for RAG vector databases

claude-chroma

Ingest Claude AI conversation exports into a local ChromaDB vector database for semantic search

cohere-compass-sdk

Cohere Compass SDK

couchbase-haystack

Couchbase haystack integration

crewai-endee

Endee vector database integration for CrewAI agent memory

datapizza-ai-embedders-cohere

Cohere embedder for the datapizza-ai framework

datapizza-ai-embedders-mistral

Mistral embedder for the datapizza-ai framework

datapizza-ai-embedders-openai

OpenAI embedder for the datapizza-ai framework

datapizza-ai-rerankers-cohere

Cohere reranker for the datapizza-ai framework

datus-storage-base

Abstract interfaces for Datus storage backends (vector & RDB)

datus-storage-postgresql

PostgreSQL RDB and pgvector backend adapters for datus-agent

dspy-qdrant

Qdrant powered retriever for DSPy

duckdb-haystack

Haystack document store and retriever for DuckDB VSS

elasticsearch-haystack

Haystack 2.x Document Store for ElasticSearch

elasticsearch2-haystack

An elasticsearch2 compatible backend for Haystack

embcli-cohere

cohere plugin for embcli

embcli-gemini

gemini plugin for embcli

embcli-llamacpp

llama-cpp-python plugin for embcli

embcli-mistral

mistral plugin for embcli

embcli-openai

openai plugin for embcli

encrypted-storage

Easy, cryptographically secure storage on numerous database backends.

enstoragemanager
eurelis-langchain-solr-vectorstore

Library that provide a Solr based vector store for Langchain

faiss-haystack

An integration of FAISS (library for efficient similarity search of dense vectors) with Haystack

fastembed-haystack

Haystack 2.x component to embed strings and Documents using fastembed embedding model

flying-delta-embeddings-openai

llama-index embeddings openai integration

flying-delta-postprocessor-cohere-rerank

llama-index postprocessor cohere rerank integration

git-rag-embedder

Minimalist library to convert Git repositories and local directories into embeddings

gllm-datastore-binary

A library containing data store components for Gen AI applications.

graphrag-vectors

GraphRAG vector store package.

halflife-rag

Temporal-aware re-ranking engine for RAG

haystack-ai-cassandra

Cassandra integration for Haystack AI with ANN vector search via SAI (Cassandra 5.0+)

haystack-bm25

Various BM25 algorithms for document ranking

haystack-hybrid-embedding

Sparse-Dense Embeddings for Pinecone in Haystack

haystack-redis

Use redis as a persistence layer for Whoosh and Haystack

hnswlib-noderag

hnswlib adapted for Node RAG project

instructor-embedders-haystack

Haystack 2.x component to embed strings and Documents using Instructor embedding model.

isaacus-haystack

Isaacus embedders for Haystack 2.x

jsonllm

Turn silly json into intelligent embeddings

just-semantic-search-agent

Semantic and hybrid search agent

kamimind-storage

Python SDK for Kamimind Storage Service

kara-storage

Kara Storage SDK

ks-llm-ranker

A Python library for knit_space operations.

lancedb-haystack

LanceDB backed datastore and retrievers for Haystack 2.X

langchain-actian-vectorai

An integration package connecting Actian VectorAI DB and LangChain

langchain-aerospike

LangChain integration for Aerospike Vector Store

langchain-alibabacloud-mysql

An integration package connecting AlibabaCloud RDS MySQL (with Vector support) and LangChain

langchain-arangodb

An integration package connecting ArangoDB and LangChain

langchain-arcadedb

An integration package connecting ArcadeDB and LangChain.

langchain-arqondb

LangChain integration for ArqonDB — VectorStore, ChatHistory, and GraphStore backed by a single self-hosted engine.

langchain-asteroid

An integration package connecting Asteroid and LangChain

langchain-astradb

An integration package connecting Astra DB and LangChain

langchain-azure-cosmosdb

Azure CosmosDB integrations for LangChain and LangGraph, including vector store, cache, chat history, and checkpoint.

langchain-azure-postgresql

LangChain VectorStore integrations for Azure Database for PostgreSQL

langchain-chdb

LangChain provider for chDB — vector store, document loader, chat history, and SQL backend for LangChain agents. In-process OLAP with native vectors and federation to remote ClickHouse.

langchain-chroma

An integration package connecting Chroma and LangChain.

langchain-cockroachdb

LangChain integration for CockroachDB with native vector support

langchain-coherence

LangChain integration for Oracle Coherence as a vector store.

langchain-cos-vectors

腾讯云 COS 向量存储桶(CosVectors)的 LangChain VectorStore 集成。

langchain-couchbase

An integration package connecting Couchbase and LangChain

langchain-db2

An integration package connecting Db2 vector store and LangChain

langchain-deeplake

An integration package connecting Deeplake and LangChain

langchain-dolphindb

Langchain integration for DolphinDB Vector Store

langchain-elasticsearch

An integration package connecting Elasticsearch and LangChain

langchain-endee

High Speed Vector Database for Faster and Efficient ANN Searches with LangChain

langchain-envector

LangChain VectorStore integration for Envector

langchain-faiss
langchain-firebolt

LangChain integration for Firebolt vector store

langchain-fluxvector

LangChain integration for FluxVector — 7-signal HyperSearch with TopK fusion and anti-hallucination confidence

langchain-galaxia-retriever

langchain galaxia integration

langchain-gridgain

Use GridGain as a Vector Store, Document Loader, LLM Cache, Key-Value Store and Chat Memory within LangChain. For LangGraph persistence, see langgraph-checkpoint-gridgain.

langchain-hana

An integration package connecting SAP HANA Cloud and LangChain

langchain-hana-prototype

An integration package connecting SAP Hana Cloud and LangChain

langchain-hana-retriever

LangChain BM25 and hybrid retrievers for SAP HANA Cloud

langchain-hyperspace

LangChain & LangGraph integration for HyperspaceDB v4.2 — Product-Manifold Hybrid VectorStore, KAG Graph, CheckpointSaver, Long-Term BaseStore, and Tribunal Verification

langchain-jieba

An integration package connecting Jieba and LangChain

langchain-jina

An integration package connecting Jina Late Chunking and LangChain

langchain-kdbai

Integration package connecting KDBAI and Langchain

More in Data, search & knowledge