LibreAI ENESPTDEFRRUJA
← All categories// rag

Best Open-Source RAG & Knowledge Tools

RAG pipelines, knowledge bases, and chat-with-your-documents.

100 tools · 💎 43 hidden gems

// start here

Start here

The most-starred projects in this category, plus a rotating pick of three more from deeper in the list — refreshed so the whole catalogue gets its turn in the window.

RAG & Knowledge

MarkItDown

MarkItDown — Microsoft tool that converts PDFs, Office files, images and more to clean Markdown for LLMs, MIT

★ 193.5k starsMIT
View guide →
RAG & Knowledge

Dify

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or…

★ 157.8k starsCustom (check repo)
View guide →
RAG & Knowledge

ragflow

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context…

★ 91.6k starsApache-2.0
View guide →
RAG & Knowledge

UltraRAG

A low-code MCP framework for building complex, innovative RAG pipelines — visibly, not as a black box.

★ 5.7k starsApache-2.0
View guide →
RAG & Knowledge

llm-graph-builder

Build Neo4j knowledge graphs from unstructured data using LLMs — then chat with your graph.

★ 5.3k starsApache-2.0
View guide →
RAG & Knowledge

code-graph-rag

RAG for your monorepo: query, understand and edit multi-language codebases with a knowledge graph.

★ 5.2k starsMIT
View guide →

More categories: VideoImageAudioAI MusicAI 3DClippingLocal LLMAI ChatAI AgentsAutomationProductivityDev ToolsDesignWritingSelf-HostedEasy Install

// about this category

About Best Open-Source RAG & Knowledge Tools

RAG — retrieval-augmented generation — is how you chat with your own documents instead of the model's memory. These tools ingest PDFs, notes, codebases, and websites, index them, and answer questions with citations back to the source material.

The category includes full chat-with-documents apps, pipeline frameworks for building your own retrieval stack, and knowledge-base servers meant to sit behind other tools. Quality lives in the unglamorous steps: how documents are chunked, embedded, and re-ranked before the model ever sees them.

How to choose

  • Your corpus decides the tool: a folder of PDFs wants a document app; a product wants a framework and an embedder you control.
  • Insist on citations — a RAG tool that cannot show its sources will eventually invent one.
  • Local embedding models keep private corpora private; check that the pipeline supports them.
// faq

Questions, answered

Which open-source RAG & Knowledge tools are listed here?

This page collects 100 open-source RAG & Knowledge projects curated by LibreAI — RAG pipelines, knowledge bases, and chat-with-your-documents. Each one is verified on GitHub and has its own guide page with an overview, install steps, use cases, and an FAQ, so you can judge fit, requirements, and licensing before you download anything.

Are these RAG & Knowledge tools free to use?

Yes. Every tool here is open source and free to download and use under its own license — most use MIT, Apache-2.0, or GPL-3.0, and any custom source-available license is flagged on the tool's page. Check the LICENSE file before commercial use.

Does LibreAI host these tools?

No. LibreAI publishes guides only — no downloads are served from this site, and no tool here is mirrored or repackaged by us. Every install comes from the project's official GitHub repository, which each guide links to directly, so you always get the genuine, current release from the people who build and maintain the tool.

How do I install a RAG & Knowledge tool from this page?

Open the tool's guide and follow its 'Run it yourself' section — the steps come from the project's own documentation — or use the 'View on GitHub' button to go straight to the official repository. Each guide also states the tool's requirements first, so you can check your machine qualifies before downloading anything.

How were these tools chosen?

Every project is verified live through the GitHub API — stars, forks, license, and recent activity — and listed only if it has real momentum and an active community. Projects are re-checked as the catalogue is refreshed, and any project that goes quiet or changes its licensing terms has that noted on its page.

What kinds of documents can RAG tools use?

Typically PDFs, office documents, Markdown and text files, web pages, and in developer-focused tools, entire codebases. Messy scans and complex tables are the weak spot everywhere — clean source documents give noticeably better answers. Most tools index a folder you point them at, so organising the source library first pays off in every answer afterwards.

Why does my RAG tool sometimes answer from the wrong passage?

Retrieval, not the language model, is usually at fault: chunking split the answer across pieces, or the embedding matched a similar-but-wrong passage. Frameworks in this category expose those knobs; app-style tools hide them but may tune them well by default.