“retrieval”

Open-source context retrieval layer for AI agents

RAGFlow: A powerful Retrieval-Augmented Generation with enhanced Agent capabilities in Go

SoTA production-ready AI retrieval system.

Vectorizer AI's Document Indexing Tool using Reasoning

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

LightRAG: Simple and Fast Retrieval-Augmented Generation

Repository showcasing advanced techniques for Retrieval-Augmented Generation (RAG) systems.

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications.

A powerful MCP toolkit for coding with semantic retrieval and editing capabilities

Memory layer for AI Agents

All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data.

Distributed vector search for AI-native applications

Langchain-Chatchat is a local knowledge-based RAG and Agent application for LLMs like ChatGLM, Qwen and Llama.

Graph-based Retrieval-Augmented Generation (RAG) system

Sub-millisecond vector & lexical search in Rust

LLM-powered knowledge curation and report generation

FastGPT is a knowledge-based platform for developing and deploying complex question-answering systems using LLMs, offering out-of-the-box capabilities like data processing, RAG retrieval, and visual A

Ultra-lite & Super-fast Python library for re-ranking search results.

RAG on Everything with LEANN

Developer-friendly embedded retrieval library for multimodal AI

Data-Driven Evaluation for LLM-Powered Applications

FlashRAG: A Python Toolkit for Efficient RAG Research

Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies.

Motorhead is a memory and information retrieval server for LLMs (DEPRECATED)

Neum AI is a best-in-class framework for managing vector embeddings at large scale.

AI Chat Platform for LLMs

An open-source RAG-based tool for chatting with documents

VectorHub: A Learning Hub for Vector Retrieval in ML

Private AI platform for agents, assistants and enterprise search

Open-source vector database for semantic search

Convert documents to structured data effortlessly

Agent S: Use Computer Like a Human

Pocket Flow: A minimalist, 100-line LLM framework for building and orchestrating AI agents.

MemOS: Self-evolving memory OS for LLM & AI Agents

ConardLi's open-source Skills collection

Summary of the world's best LLM resources.

Visual Retrieval-Augmented Generation

Local persistent memory store for LLM applications

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.