JSPM

Core LangChain.js abstractions and schemas

OpenAI integrations for LangChain.js

Typescript bindings for langchain

Promptbook: Run AI apps in plain human language across multiple models and platforms

Anthropic integrations for LangChain.js

Mastra is the Typescript framework for building AI agents and assistants. It’s used by some of the largest companies in the world to build internal AI automation tooling and customer-facing agents.

Smart. Simple. Local. AI-powered semantic search in TypeScript using transformer embeddings. No cloud, no API keys — 100% offline.

Node.js bindings for faiss

Official JavaScript library for Tavily.

Performant search algorithm optimized for descriptive texts

The Retrieval-Augmented Generation (RAG) module contains document processing and embedding utilities.

NodeJS implementation of @Qdrant/fastembed

typescript and wasm bindings for Hnswlib

Promptbook: Run AI apps in plain human language across multiple models and platforms

a vector similarity search engine in WASM

Universal Knowledge Protocol™ - World's first Triple Intelligence database unifying vector, graph, and document search in one API. 31 nouns × 40 verbs for infinite expressiveness.

Promptbook: Run AI apps in plain human language across multiple models and platforms

🧠 AI Memory System powered by MongoDB Atlas & Voyage AI - Autonomous memory management with zero manual work

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Interfaces for extending the embedjs ecosystem

Promptbook: Run AI apps in plain human language across multiple models and platforms

Transform any GitHub repository into searchable vector embeddings. MCP server with smart indexing, voyage-context-3 embeddings, and semantic search for Claude/Cursor IDEs.

Voyage AI Provider for running Voyage AI models with Vercel AI SDK

n8n community node for LM Studio Embeddings API with encoding format selection

Useful util functions when extending the embedjs ecosystem

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

PDF loader for embedjs

A rag component for Convex.

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Word, PPT and Excel loader for embedjs

Sitemap recursive loader for embedjs

Load images into embedjs

CSV loader for embedjs

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

XML loader for embedjs

Promptbook: Run AI apps in plain human language across multiple models and platforms

Add LibSQL support to embedjs

Web page loader for embedjs

RAG search system for Gist, GitHub, and Local Files.

A lightweight CLI tool for testing RAG (Retrieval-Augmented Generation) systems with different embedding combinations

typescript and wasm bindings for Hnswlib

XML loader for embedjs

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

MemorAI Advanced MCP Server - CBD-Based High-Performance Vector Memory System with HTTP/SSE Support

Solar LLM and Embeddings nodes for n8n

Promptbook: Run AI apps in plain human language across multiple models and platforms

A NodeJS RAG framework to easily work with LLMs and custom datasets

Enable usage of OpenAI models with embedjs

Enable usage of Ollama with embedjs

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

MCP server for integrating Turso with LLMs

Promptbook: Run AI apps in plain human language across multiple models and platforms

Orama plugin for generating embeddings securely on the front-end

Promptbook: Run AI apps in plain human language across multiple models and platforms

Official Typescript API client library for turbopuffer.com

Performant search algorithm optimized for descriptive texts

Promptbook: Run AI apps in plain human language across multiple models and platforms

Vercel AI SDK Provider for Ollama using official ollama-js library

> A lightweight, AI-powered npm package finder — directly from your terminal.

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

Promptbook: Run AI apps in plain human language across multiple models and platforms

Transform any GitHub repository into searchable vector embeddings. MCP server with smart indexing, voyage-context-3 embeddings, and semantic search for Claude/Cursor IDEs.

Promptbook: Run AI apps in plain human language across multiple models and platforms

Fast, easy-to-use AI text embeddings, optimized for serverless functions.

Pre-trained English-language model weights for `@energetic-ai/embeddings`.

A client side vector search library

JavaScript SDK for AgentDB database service

n8n community node for Milvus vector database with enhanced metric type switching

A NodeJS RAG framework to easily work with LLMs and custom datasets

Gentrace Pinecone v1 plugin for Node.JS

Codai Better Database - High-Performance Vector Memory System with HPKV-inspired architecture and MCP server

Production-ready MCP server with complete agent integration, multi-transport support, and comprehensive development automation tools for AI-assisted workflows.

Ziri — AI code context CLI (per-repo stores, streaming embeddings, multi-repo registry)

AI toolkit by Q9Labs with vector search, memory, and deep search utilities

Open Source Alternative for Building End-to-End Vector Search Applications without OpenAI & Pinecone

Get millions of financial documents into your AI app 🚀

AI Memory MCP Server - Persistent memory and codebase understanding for AI coding assistants

EnergeticAI is TensorFlow.js, optimized for serverless environments, with fast cold-start, small module size, and great usability.

The easiest way to use LLMs, including streams, images, documents, tools and various agent scenarios.

An intelligent code compliance checker and embedding search tool for Claude Code

Typescript bindings for langchain

Typescript bindings for langchain

AI-powered hexagonal framework with OpenAI integration, database adapters, web scraping, and Next.js demo application

GigaChat integration for LangChain.js

MCP server for searching Hex package documentation

Simple text embeddings library

Central Nervous System MCP Server for Autonomous Multi-Agent Orchestration with free local embeddings

Tiny helper to generate sentence-transformers embeddings via @xenova/transformers in Node.js and the browser.

Interfaces for extending the embedjs ecosystem

Lightweight Cosine Similarity Function. Built as an alternative to the compute-cosine-similarity package. Works with high dimension vectors like openAI embeddings

Public types, enums and options used by Llumiverse API.

Mixedbread AI Provider for running Mixedbread AI models with Vercel AI SDK

Typescript bindings for langchain

Useful util functions when extending the embedjs ecosystem

Advanced n8n node for Puter.js AI with RAG agentic capabilities, document processing, audio transcription, Supabase integration, and cost-optimized model priorities

A service for calculating, managing, truncating openai prompt tokens

Brain MCP Server - Semantic knowledge base access for Claude Code via Model Context Protocol. Provides intelligent search and navigation of files from multiple locations through native MCP tools.

CLI tool for managing the Mixedbread platform.

typescript and wasm bindings for Hnswlib

Zero-dependency, modular SDK for building robust natural language applications

Client for the Vectorize API

Web page loader for embedjs

PDF loader for embedjs

Core indexing and search functionality for h-codex

Enable usage of OpenAI models with embedjs

Provide an universal API to LLMs. Support for existing LLMs can be added by writing a driver.

MCP server for semantic code search powered by MongoDB Atlas Vector Search and Voyage AI embeddings

Composable TypeScript toolkit for LLM pipelines, semantic chunking, and AI workflow orchestration.

Core vector search engine for code intelligence

JavaScript NAPI bindings for faiss

Run AI models anywhere.

Word, PPT and Excel loader for embedjs

TypeScript client library for AI Search API - search and retrieve intelligent responses with context awareness

Semantic Web Memory for Intelligent Agents

Stateful AI agent memory layer for PostgreSQL with pgvector - TypeScript-first with intelligent context management

A lightweight and efficient vector database for storing and searching text embeddings in the browser's local storage. The package uses OpenAI's API to generate embeddings for text documents and provides functionality for similarity search, filtering, and

A TypeScript MCP server for document management and semantic search with embeddings

PAMPA – Protocol for Augmented Memory of Project Artifacts (MCP compatible)

Orama plugin for generating embeddings locally

Neural Vector Database for efficient similarity search

In-memory vector database

MCP server for SwiftOpenAI - access OpenAI APIs through Model Context Protocol

MCP tool for storing and searching memories with semantic search capabilities

Production-ready RAG (Retrieval-Augmented Generation) framework for Next.js applications with PostgreSQL + pgvector

Best-in-class MCP (Model Context Protocol) server for AI memory storage with MIRIX-Inspired Specialized Memory Types (Core, Episodic, Semantic, Procedural, Resource, Knowledge Vault), Progressive Disclosure, AI-Powered Summaries, Context Window Optimizati

Add LanceDb support to embedjs

CSV loader for embedjs

A CLI tool for storing and searching development memories, insights, and patterns using Supabase and OpenAI embeddings

Sitemap recursive loader for embedjs

n8n community sub-node for Google Gemini Embeddings with extended features like output dimensions support

SDK for interacting with RagFlow API

XML loader for embedjs

Hybrid semantic router with BM25 + dense embedding search

Add MongoDB support to embedjs

Load images into embedjs

Add LibSQL support to embedjs

Automatically and continuously vectorize your PostgreSQL tables with the flexibility of your own embedding pipelines

n8n community node for SAP HANA Vector Store integration with LangChain

Official TypeScript client library for Lunos AI API - A comprehensive AI proxy service supporting chat completions, image generation, audio synthesis, embeddings, and more.

n8n community node for SiliconFlow AI models - chat completions, vision language models, embeddings, and reranking

Jina AI Provider for running Jina AI models with Vercel AI SDK

Enhanced Google Gemini embeddings node for n8n with direct API integration and custom dimensions support

MCP server for enhanced Qdrant vector database functionality

n8n community sub-node for Google Vertex AI Embeddings with output dimensions and configurable batch size support - resolves LangChain compatibility issues

LLM driver implementations. Currently supported are: openai, huggingface, bedrock, replicate.

XML loader for embedjs

Intelligent AI Gateway for routing requests to optimal language models with Vercel AI SDK provider support

n8n nodes for SAP AI Core LLM and embeddings integration

Vector search SDK for LibSQL

TypeScript SDK optimized for GPT-OSS 20 and GPT-OSS 120 models - High-performance training and inference

Youtube transcript and channel recursive loader for embedjs

Vector search with HNSWlib and SQLite in TypeScript.

The TypeScript Code Extractor and Analyzer can be handy for RAG (Retrieval-Augmented Generation) systems for codebases. It provides a detailed and structured representation of the codebase that can be converted into embeddings, enabling more effective adv

Enable usage of Ollama with embedjs

Simplified advanced memory engine - no tiers, just powerful semantic search with persistence

Official TypeScript/JavaScript SDK for EdgeVector - Edge-native multi-paradigm database with AI-first features

Official TypeScript/JavaScript SDK for EdgeVector DB - A globally distributed, edge-native database platform combining document storage, vector search, time series, and real-time streaming

Advanced n8n node for Agentic RAG with Supabase pgvector - handles structured/unstructured documents with AI-powered query refinement

MCP server for codebase indexing with Voyage AI embeddings and Qdrant vector storage

Add HNSWLib support to embedjs

n8n nodes for OpenRouter AI API integration

Lightning-fast Euclidean distance search using locality-sensitive hashing. Compress high-dimensional vectors into tiny fingerprints for 10× faster similarity search with 99% less memory usage.

Lightning-fast cosine similarity search using locality-sensitive hashing. Compress high-dimensional vectors into tiny fingerprints for 10× faster similarity search with 99% less memory usage.

Official TypeScript/JavaScript SDK for EdgeVector - Edge-native multi-paradigm database with AI-first features

Official TypeScript/JavaScript SDK for Hashub Vector API - High-quality multilingual text embeddings with Turkish excellence

A fast, client-side vector search and embedding library.

Vercel AI SDK対応のインメモリRAG実装 - In-memory RAG implementation with Vercel AI SDK support

SPARC 2.0 - Autonomous Vector Coding Agent + MCP. SPARC 2.0, vectorized AI code analysis, is an intelligent coding agent framework built to automate and streamline software development. It combines secure execution environments, and version control into a

The easiest way to use LLMs, including streams, images, documents, tools and various agent scenarios.

MongoDB-powered Memory Bank MCP server with hybrid search capabilities for AI assistants

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

AI-powered code intelligence with semantic search and natural language querying

Custom embedding node for n8n to work with Supabase Vector Store

Typescript bindings for langchain-gpt4all

MCP server for the Mixedbread Platform

LU (Layer Understanding) is a lightweight framework for controlled chatbot interactions with LLMs, action orchestration, and retrieval-augmented generation (RAG).

Confluence loader for embedjs

Unified SDK for AI-powered context and personalization

The memory layer for Personalized AI in Typescript

Unified SDK for AI agent personalization

Run AI prediction functions in your JavaScript and Node.js apps.

Relationships between Backbone models in the flavor of MongoDB's document references and embeddings

A code context tool with vector search and real-time monitoring, with optional Git integration.

n8n node for OpenAI Analytics

DataStax RAGStack for Javascript/Typescript

The intelligent context optimization system for AI coding assistants. Built with Cole's PRP methodology, Context Portal knowledge graphs, and production-ready MongoDB architecture.

MCP server with SQLite vec0 and Ollama embeddings for graph-based semantic memory

Convenient interface for utilizing various embedding models via API and locally.

embeddings service for chatluna

Enable usage of HuggingFace models with embedjs

Add Qdrant support to embedjs

A TypeScript/JavaScript module for implementing Retrieval-Augmented Generation (RAG) using Qdrant vector database, Google's Generative AI embeddings, and Groq LLM.

RAG (Retrieval Augmented Generation) library for MongoDB Vector Search

The core foundation of the Mastra framework, providing essential components and interfaces for building AI-powered applications.

Add Pinecone support to embedjs

NodeJS client for worka

Fast, type-safe utilities for vector embedding comparison and search.

Open Source Alternative for Building End-to-End Vector Search Applications without OpenAI & Pinecone

MCP server for RAG-based document search and management

Add Redis support to embedjs

Heroku Managed Inference and Agents provider for the Vercel AI SDK

Promptbook: Run AI apps in plain human language across multiple models and platforms

Add LMDB support to embedjs

DataStax RAGStack CLI

Enable usage of Node-Llama-Cpp with embedjs

A library for creating and managing embeddings with PCA and k-means clustering.

A NodeJS RAG framework to easily work with LLMs and custom datasets

MCP Rag search of the customer related informations

n8n community node for Zilliz vector database with full RAG support

Add CosmosDB support to embedjs

A LangChain-based tool to answer questions strictly from PDF content using Groq LLM and local embeddings.

🏠 Teach AI to understand natural language like a patient tutor. Advanced embedding-based function calling with semantic understanding, confidence scoring, and natural language parameter extraction.

Matches a given phrase to the best match in a database and determines the wildcards using a slot filler. This is like a regex, but much more flexible for phrase matching and alignment.

A lightweight memory-based vector store with persistent storage support for both Node.js and browser environments. Efficiently store, retrieve, and search vector embeddings with minimal dependencies.

The core foundation of the Mastra framework, providing essential components and interfaces for building AI-powered applications.

The Retrieval-Augmented Generation (RAG) module contains document processing and embedding utilities.

Simple neural sentence search.

Enhanced vector database with HNSW indexing, WAL, error recovery, and production-ready features. Based on Vectra by Steven Ickman.

High-performance Node.js client for Antarys vector database with HTTP/2, connection pooling, and intelligent caching

Enable usage of Cohere models with embedjs

A toolkit for AI based conversations

AI in payload

Typescript bindings for langchain

Typescript bindings for langchain

Typescript bindings for langchain

A robust LLaMA Node.js library with enhanced error handling and segfault fixes

(Unofficial) Voyage AI Embeddings node for n8n

MCP server for Milvus vector database with semantic and full-text search capabilities

A NodeJS RAG framework to easily work with LLMs and custom datasets

Fast, easy-to-use AI few-shot text classification.

A TypeScript SDK for embedding generation

N8N node for generating text embeddings using Transformer.js with direct text input

A powerful memory stack for AI applications with vector embeddings

Add Weaviate support to embedjs

tSNE is a dimension reduction and vector projection method. It's main use is in visualizing high-dimensional vectors, such as text embeddings, in 2D or 3D plots.

MCP server to search qdrant database

Automatically tag your Hexo posts with GPT-3｜使用GPT-3自动为Hexo文章添加标签

A tool to process markdown files from GitHub repositories and store them in Upstash Vector