Open Source RAG Projects
Discover 51 open source RAG repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. RAG projects here are most often combined with Python, AI and LLM. Last updated October 3, 2026.
51 repositories · updated October 3, 2026
rag-zero-to-hero-guide: Learn Retrieval-Augmented Generation
A learning guide to retrieval-augmented generation, from core concepts to evaluation and advanced approaches. It combines explanations, Jupyter notebook implementations, tool references, and survey papers for learners building RAG knowledge.
griptape: Build AI Agents and Workflows in Python
Griptape is a modular Python framework for building generative AI applications with tasks, agents, pipelines, and workflows. It suits developers who want to combine language models with tools, memory, and retrieval components through swappable integrations.
RAGChecker: Diagnose Retrieval-Augmented Generation Systems
RAGChecker evaluates RAG pipelines with overall, retriever, and generator metrics. It is for developers and researchers who need to identify whether retrieval or generation is driving quality problems and guide targeted improvements.
rerankers: Use Diverse Reranking Models Through One Python API
rerankers provides a shared Python interface for reranking documents with cross-encoders, LLM-based methods, and hosted APIs. It suits developers building retrieval systems who want to compare or switch rerankers without adapting their application to each model's interface.
LazyLLM: Low-Code Development for Multi-Agent LLM Applications
LazyLLM offers a low-code development tool designed for building multi-agent LLM applications with ease. It simplifies the creation of complex AI applications, providing a streamlined workflow for rapid prototyping, data feedback, and iterative optimization. Developers can leverage its extensive features for deployment, cross-platform compatibility, and efficient model fine-tuning.
PixelRAG: Search Documents by Their Visual Content
PixelRAG indexes screenshots of web pages and documents for visual retrieval, preserving charts, tables, and layout that text extraction can lose. It offers a Python pipeline, command-line renderer, and hosted search API.
opendataloader-pdf: Extract Structured Data and Accessibility Tags from PDFs
OpenDataLoader PDF parses digital, scanned, and tagged PDFs into structured formats for AI and document workflows. It also automates conversion of untagged PDFs into Tagged PDFs, with optional hybrid processing for complex documents.
claude-mem: Preserve Agent Context Across Sessions
Claude-Mem captures and summarizes agent activity, then retrieves relevant project history in later sessions. It is for developers who want coding agents to retain useful context instead of starting from scratch each time.
Graphify: Transform Your Codebase into a Queryable Knowledge Graph
Graphify is an innovative AI coding assistant skill that converts any codebase, documentation, and even multimedia files into a queryable knowledge graph. This powerful tool allows developers to navigate complex projects by querying relationships between components, rather than manually searching through files. It integrates seamlessly with popular AI assistants, providing deep insights and streamlining development workflows.
rag-from-scratch: Learn Retrieval-Augmented Generation Step by Step
A Jupyter notebook series that teaches the building blocks of retrieval-augmented generation, from indexing and retrieval to generation. It is aimed at learners who want to understand RAG concepts through an educational progression rather than adopt a ready-made application.
Article-Assistant--RAG-Telegram-Bot: Ask Questions About Documents
A Telegram bot that turns web articles, PDFs, text files, and YouTube transcripts into searchable knowledge bases. It uses retrieval-augmented generation to answer questions with source citations and can also create summaries.
Qwen-Agent: Build Tool-Using LLM Applications
Qwen-Agent is a Python framework for building Qwen-based assistants that can call tools, plan tasks, and work with documents. Use it to prototype or deploy agent applications when you need integrations such as MCP, code execution, or retrieval-augmented generation.