Retrieval agents

Interface between LLMs and your data

A Python package for automating interactions with ChatGPT using Selenium. Chatgpt automation without api…

This library provides a comprehensive suite of metrics to evaluate the performance of Retrieval-Augmented…

FinRAG: Financial Retrieval Augmented Generation

Infer planet properties using AGNI as a static structure model

A comprehensive RAG (Retrieval-Augmented Generation) toolkit for AI applications

A pipeline for question answering and retrieval-augmented generation (RAG)

A dead simple RAG pipeline with persistent memory and conversation namespaces.

A comprehensive toolkit for building Retrieval-Augmented Generation (RAG) pipelines, including data loading…

RAGLink是一个开源的Retrieval-Augmented Generation框架，旨在通过结合检索和大模型生成技术，提升自然语言处理任务的性能和效率。为用户提供了一个强大、灵活且易于扩展的开发环境。

RAGScraper is a Python library designed for efficient and intelligent scraping of web documentation and…

Library to facilitate the use of state-of-the-art retrieval models in common RAG contexts.

A modular Retrieval-Augmented Generation (RAG) library integrating Vertex AI, OpenAI, and ChromaDB.

A simple Retrieval-Augmented Generation (RAG) library using Hugging Face datasets.

High-performance retrieval augmented generation components for the AccuralAI ecosystem.

Advanced Retrieval Framework — dependency-free retrieval pipeline toolkit

A lightweight package scaffold for the ag-rag project.

Agent Brain CLI - Command-line interface for managing AI agent memory and knowledge retrieval

The Agent Lifecycle Toolkit (ALTK) is a library of components to help agent builders improve their agent with…

Inspect, compare, and evaluate vector retrieval — MRR, Recall@k, and rank diff in one library

Agentic RAG framework - Coming soon. Part of the AIH-Infra ecosystem.

Local documentation retrieval service for agent-assisted development. Indexes framework docs into typed…

Agent context SDK — persistent memory and structured retrieval for any AI application. Powered by Redis.

A comprehensive, professional-grade agentic Retrieval-Augmented Generation (RAG) library — core building…

Automate & accelerate AI research with Python! Focus on experiments, not setup, with smart topic planning…

AIH Agentic RAG framework - Coming soon. Part of the AIH-Infra ecosystem.

Graph-based RAG framework - Coming soon. Part of the AIH-Infra ecosystem.

Pointer-based skill retrieval for LLM agents. Alternative to vector DB RAG.

Standalone Model Context Protocol (MCP) server for Amazon Bedrock Knowledge Base Retrieval

Python client sdk of AMD PER RAG. AMD PER RAG is an open-source RAG (Retrieval-Augmented Generation) engine…

ATI LlamaIndex integration: retrieval/synthesis callbacks -> ATI spans

AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for…

A modular, research-backed RAG building block library

Stop retrieving chunks. Start retrieving facts. Graph-based RAG that breaks documents into atomic knowledge…

Lightweight, LLM-agnostic RAG pipeline with pluggable corpora. Works with Claude, Gemini, or any LLM.

AutoRAG is a flexible and scalable solution for building Retrieval-Augmented Generation (RAG) systems.

A CLI tool that automates RAG hyperparameter optimization using Bayesian search and synthetic data generation

An AWS Labs Model Context Protocol (MCP) server for Bedrock Knowledge Base Retrieval

An AWS Labs Model Context Protocol (MCP) server bedrock-kb-retrieval expert

Production RAG pipeline — grounded retrieval, source-cited answers, Precision@k + MRR eval

Citation-verified RAG service with deterministic + semantic claim verification.

General-purpose open-source RAG engine with multi-LLM, hybrid retrieval, GraphRAG, and MCP support

Contains Retrieval Augmented Generation related utilities for Azure Machine Learning and OSS interoperability.

Interface between LLMs and your data

BRAG — Better RAG. Same API. Better results.

Production RAG pipeline with vector retrieval, configurable chunking, and evaluation harness

Compatibility bridge for the legacy bijux-rag PyPI package. Preserves installs, imports, and the bijux-rag…

Security middleware for Python LLM apps and services. Blocks prompt injection, masks PII, inspects outputs…

Build-your-own Retrieval-Augmented Generation (RAG) system

Improve development of retrieval augmented generation (RAG) applications at the BR AI + Automation Lab.

An efficient python library for building AI applications using the Retrieval-Augmented Generation (RAG)…

Lossless text compression, storage, memory management, and retrieval toolkit

ChatBot with Retrieval Augmented Generation

Automated ChatGPT account signup using Outlook email stock with IMAP OTP retrieval

Open-source local-first context compression and token reduction pipeline for Claude Code with hybrid…

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI…

Production-ready RAG agent for intelligent code retrieval and question answering

Build knowledge graphs from your codebase for LLM context retrieval — supports PHP, JavaScript, and…

Vectorless RAG for Code Repositories - Navigate your codebase with LLM reasoning

A powerful integration between LangGraph and Cognee providing intelligent knowledge management and retrieval…

Cognitive Thought and Retrieval Augmented Generation - An advanced AI agent framework combining CoTAEngine…

Domain-Adaptive Meta-Learning RAG Framework for Vertical Domain AI Applications

DeepLightRAG: High-performance Document Indexing and Retrieval System (use with any LLM)

Haystack integration for Dewey — document store, retriever, and research component

End-to-end GraphRAG toolkit that takes you from raw documents to a knowledge graph and then to…

Installable RAG infrastructure for Django projects.

DocRag: An advanced document search and retrieval system leveraging Retrieval-Augmented Generation for…

DSPy retriever modules for Built-Simple research APIs (PubMed, ArXiv, Wikipedia)

Extends RAG with structured query capabilities using dual vector + relational storage

A reusable and configurable RAG (Retrieval-Augmented Generation) pipeline.

RAG in 3 lines of code — load documents, ask questions, get answers

Retrieval-Augmented Generation - (RAG)

An LLM-based Retrieval-Augmented Generation (RAG) component for education, supporting problem solving…

LangChain retriever integration for Egnyte document search and retrieval

Embedding-Less retrieval with Iterative Text Exploration (ELITE)

Simplest open source retrieval (RAG) framework

Simplest open source retrieval (RAG) framework

Simplest open source retrieval (RAG) framework

Simplest open source retrieval (RAG) framework

Cross-industry compliance patterns for RAG pipelines: FERPA, HIPAA, GDPR, NIST AI RMF, OWASP LLM Top 10, and…

Entropy-regulated retrieval-augmented reasoning system inspired by diffusion physics.

A comprehensive evaluation toolkit for assessing Retrieval-Augmented Generation (RAG) outputs using…

XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented…

Official Python SDK for the RAGify RAG-as-a-Service API

A Python library for Retrieval-Augmented Generation (RAG) capabilities in LLM applications.

An Efficient Retrieval Augmentation and Generation Framework for Intel Hardware.

Simplified fine-tuning of retrieval-augmented generation (RAG) systems.

A comprehensive RAG framework with Arabic language support, multi-provider embeddings, and advanced RAG…

A library for efficient Retrieval-Augmented Generation research

Flexible RAG (Retrieval-Augmented Generation) framework for building AI applications.

Fully automated RAG SDK - Initialize with a directory and start querying

Retrieval augmentation for humans

A powerful graph-based RAG framework (foxHippoRAG distribution) that enables LLMs to identify and leverage…

Local-first RAG indexer for repos, docs, and PDFs

Hybrid retrieval-augmented generation — graph × vectorstore → enriched context. Placeholder release.

Production-grade Python toolkit for building GDPR-compliant RAG systems with automatic PII detection, audit…

Unofficial Gemini API with Firefox cookie auto-retrieval and easy chat client.

Graph Foundation Model for Retrieval Augmented Generation

An open-source, high-transparency modular RAG framework for AI/ML applications

GPT RAG (Retrieval-Augmented Generation) common library

GPT RAG (Retrieval-Augmented Generation) common library

A simple package for implementing RAG

GraphRAG: A graph-based retrieval-augmented generation (RAG) system.

GraphRAG Ecolink: A graph-based retrieval-augmented generation (RAG) system.

The most accurate Graph RAG framework. Build knowledge graphs and query them with natural language. Built on…

GraphRAG: A graph-based retrieval-augmented generation (RAG) system.

High-performance RAG pipeline for GRASS GIS with >90% accuracy and <5s response time

Client library for Enterprise h2oGPTe

Haystack integration for Built-Simple research APIs (PubMed, ArXiv)

A hierarchical RAG framework for chunks retrieval.

AI-Powered Legal Document Retrieval Engine based on Hierarchical Clustering & RAG

A powerful graph-based RAG framework that enables LLMs to identify and leverage connections within new…

A powerful graph-based RAG framework that enables LLMs to identify and leverage connections within new…

Local-only RAG benchmarking CLI — measures recall, MRR, chunk overlap, latency, and BEIR IR metrics

HydRAG — Multi-Headed Retrieval-Augmented Generation with CRAG supervision

A RAG-based HR chatbot with MCP server for document retrieval and email functionality

MCP server for code retrieval from a fully indexed codebase using CocoIndex

MCP server for search and retrieval of web crawler content

A Retrieval-Augmented Generation (RAG) system that indexes the OWASP Web Security Testing Guide (WSTG) into a…

Indox Retrieval Augmentation

Indox Retrieval Augmentation

A RAG (Retrieval-Augmented Generation) library for document processing and retrieval.

RAG pipelines with InterSystems IRIS as the vector database. Six strategies (basic, rerank, CRAG, GraphRAG…

Tool retrieval and ranking algorithms for LLM agents

SAGE RAG Framework - Document loaders, chunkers, retrievers for RAG pipelines

RAG benchmarking suite for the SAGE ecosystem

Retrieval Augmented Generation (RAG) starter library

Local RAG System for Claude Code — Hybrid search + Cross-encoder Reranking + 12 MCP Tools + 20 Format…

A Retrieval-Augmented Generation (RAG) framework with MongoDB and Sentence Transformers

A search engine using machine learning models and Elasticsearch for advanced document retrieval.

A flexible Retrieval-Augmented Generation framework by Ksschkw

A label-driven RAG pipeline built on top of paralabelgen.

Uma biblioteca Python leve para RAG (Retrieval-Augmented Generation) compatível com LangChain, que não requer…

LangChain integration for Built-Simple research APIs (PubMed & ArXiv)

LangChain integration for Dewey — retriever, vector store, and research tool

A langchain integration package with retrieval capabilities for EuropePMC

LangChain integration for Nebius AI Studio

LangChain integration for Parallel Context-of-Experts Decoding (PCED) for RAG pipelines

An integration package connecting Perigon and LangChain

An integration package connecting Vectorize and LangChain

LD-RAG: GPT-driven ontology reasoning and retrieval

The Lightning Library for LLM Applications.

LightRAG: Simple and Fast Retrieval-Augmented Generation

LightRAG: Simple and Fast Retrieval-Augmented Generation

GitHub retrieval and context generation utilities for coding assistants and AI developer workflows.

Interface between LLMs and your data

Interface between LLMs and your data

Interface between LLMs and your data

LlamaIndex integration for OneBrain — persistent AI memory layer

llama-index packs chroma_autoretrieval integration

llama-index packs deeplake_multimodal_retrieval integration

llama-index packs dense_x_retrieval integration

This template contains a reference architecture for Retrieval Augmented Generation against a set of documents…

llama-index packs multidoc_autoretrieval integration

llama-index packs raptor integration

llama-index packs timescale_vector_autoretrieval integration

llama-index packs vectara_rag integration

llama-index packs voyage_query_engine integration

LlamaIndex retriever integration for Dewey — managed RAG backend

llama-index retrievers Vectorize.io integration

Interface between LLMs and your data

LlamaIndex VectorStore for VelesDB: The Local AI Memory Database. Microsecond RAG retrieval.

Interface between LLMs and your data

State-contracted verification and explainable retrieval gating for agentic RAG.

Deterministic codebase context retrieval for LLMs

Retrieval-backed LLMs for math education

Это библиотека на Python, предназначенная для упрощения создания и управления моделями генерации с…

A precision-focused LLM-powered web research tool that prioritizes accuracy over quantity

Using LLM to parse PDF and get better chunk for retrieval

High-performance document memory system with vector search capabilities for Python applications

A modular text-based database manager for retrieval-augmented generation (RAG), seamlessly integrating with…

Neural Retrieval-Augmented Generation for GitHub code blocks

Interface between LLMs and your data

Hierarchical Retrieval-Augmented Generation with Haystack

A unified Neo4j MCP server for GraphRAG: vector search, fulltext search, search-augmented Cypher queries…

MCP server for RAG (Retrieval-Augmented Generation) operations with local document indexing - Fork with…

MCP Server for rapid-rag - Local RAG with semantic search and LLM queries

A core library for Markdown-aware chunking, semantic structuring, vectorization, and RAG retrieval.

a modular Python framework for semantic search, vector indexing, and retrieval-augmented generation

A Python package for memory-augmented retrieval-augmented generation

MetaRAG: A multi-LLM ensemble Retrieval-Augmented Generation framework with cosine similarity ranking.

A lightweight RAG (Retrieval-Augmented Generation) library with document loading, chunking, embedding, vector…

MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation

The official Mixedbread AI integration for LangChain.

Evaluation framework for Multimodal Vision-Language RAG systems — measure retrieval quality, hallucination…

MODE organizes documents into semantically coherent clusters and uses centroid-based retrieval to deliver…

State-of-the-art RAG system with MongoDB Atlas and Voyage AI

A comprehensive, framework-agnostic library for evaluating Retrieval-Augmented Generation (RAG) pipelines.

Use late-interaction multi-modal models such as ColPali & ColQwen2 for retrieval, with Qdrant as a backend.

RAG pipeline library — chunking, embeddings, vector search, and retrieval for the Willian SaaS platform

An AWS Labs Model Context Protocol (MCP) server for Bedrock Knowledge Base Retrieval

MultiAgent Framework is a powerful Python-based system for creating and managing multi-agent conversations…

Needle RAG tools for Haystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy.

Neural Retrieval-Augmented Generation for GitHub code blocks

Subpackage for NVIDIA RAG in NeMo Agent Toolkit

This blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG)…

Simple and quick RAG (Retrieval Augmented Generation) using ollama API.