Local, cost-free vector store for text embeddings and similarity search (soon) in-browser and Node.js.

Upstash VectorStore and Redis RecordStore adapters for Crux storage.

Unified client SDK for KB Labs platform. Zero dependencies. Access LLM, Cache, VectorStore, Analytics, and any adapter through a single client.

Upstash Vector-backed VectorStore for Kuralle (edge/serverless runtime)

Cloudflare Vectorize-backed VectorStore for Kuralle (edge/Workers runtime)

LanceDB-backed VectorStore for Kuralle (Node/Bun only, not for edge runtimes)

sqlite-vec VectorStore implementation for brain-core (1536-dim, cap 8192)

Optional working memory and semantic recall primitives with Embedder/VectorStore contracts for Prism.

向量库 —— LanceDB 高性能实现

```tsx const openai = new OpenAI({ apiKey: process.env.OPENAI_KEY }); const selector = new AgenticaOpenAIVectorStoreSelector({ provider: { api: openai, assistant: { id: assistant_id }, vectorStore: { id: vector_store_id } }, });

Genkit AI framework plugin for temporary local vector database.

Weaviate integration for LangChain.js

Libsql provider for Mastra - includes both vector and db storage capabilities

Postgres provider for Mastra - includes both vector and db storage capabilities

向量库 —— 内置平面文件实现（零依赖）

DuckDB vector store provider for Mastra - embedded high-performance vector storage with HNSW indexing

YDB integration for LangChain.js — VectorStore backed by YDB.

类型/接口/能力声明包（只导出 `type` 与 `*Capabilities`，不含运行时逻辑）

Pluggable similarity search vector stores for Nanio agentic framework (v0.0.1-alpha.4)

A Model Context Protocol (MCP) server that provides semantic search capabilities across files. This server watches specified directories and creates vector embeddings of file contents, enabling semantic search across your documents.