#vector-database

The best-benchmarked open-source AI memory system. And it's free.

The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect components (LLMs, Tools, vector DBs, memory) to agents that interact with your data and UI.

Official Python SDK for the Pinecone vector database

Official Weaviate TypeScript Client

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

JavaScript/Typescript SDK for Qdrant Vector Database

An official lightweight library for the RaBitQ algorithm and its applications in vector search.

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.

Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground

A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.

Lance Namespace is an open specification for describing access and operations against a collection of tables in a multimodal lakehouse

Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

The LangChain wrapper of Milvus vector database for efficient vector search, full-text search, hybrid retrieval and RAG.

Production-ready KV-backed HNSW implementation in Rust using LMDB

Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

OpenCode plugin that gives coding agents persistent memory using local vector database

Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). Apache-2.0.

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.

The Data Control Plane for AI Agents — acquire, validate, and land data over MCP with scoped keys, approval gates, and an audit log. Self-hosted, open source.

A Python SDK for OceanBase Multimodal Store—enabling vector search, full-text search, and JSON table operations—offers both Milvus-compatible API and SQLAlchemy-based SQL mode, and supports both OceanBase and OceanBase seekdb.

Pinecone.io Golang Client

Connect your Pinecone projects to Cursor, Claude, and other AI assistants