A complete search engine and RAG pipeline in your browser, server, or edge network with support for full-text, vector, and hybrid search in less than 2kb.

Orquestador multi-agente de CLIs de IA para pipelines RAG con routing por sensibilidad, policy de proveedores y CLIs intercambiables (Claude, Codex, Gemini, Ollama, Azure, Bedrock, Vertex).

AWS SDK for JavaScript Codepipeline Client for Node.js, Browser and React Native

Transform pipeline operator into call expressions

Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 38 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).

Retrieval-Augmented Generation (RAG) and vector search for HazelJS framework

RAG primitives for Kuralle

Core RAG engine for KB Labs Mind: ingest, retrieval, answer. Dry business logic over platform adapters.

Dataset package for Workglow.

Offline HTTP RAG (Retrieval-Augmented Generation) server for the Red Sift Design System — returns ranked, scored documentation chunks for any LLM/agent to consume.

Retrivora AI is a plug-and-play AI engine for RAG chat experiences — generic vector DB + LLM provider, embeddable or standalone.

Chain functions, generators, Node streams, and Web streams into a pipeline with backpressure support.

Local RAG MCP Server - Easy-to-setup document search with minimal configuration

Scaffold a full-stack Next.js RAG (retrieval-augmented generation) chat app — create-next-app style, with workspaces, image retrieval and an admin panel, tailored to the AI providers and vector store you choose.

Command-line interface for vibe-agent-toolkit

MCP server for semantic search of GitHub issues/PRs via Cloudflare Worker

Promised out of order transform.

Abstract RAG (Retrieval-Augmented Generation) interfaces and shared implementations

AI Orchestration System - TypeScript rewrite

The official Pinecone TypeScript SDK for building vector search applications with AI/ML.