LibreAI / RAG & Knowledge / OpenDocuments
// rag · joungminsung/OpenDocuments

OpenDocuments

OpenDocuments is an open-source rag & knowledge project by joungminsung (joungminsung/OpenDocuments on GitHub). It has 115 GitHub stars and 21 forks, is released under the MIT license, and was last updated on GitHub on 26 July 2026.

Self-hosted RAG search across GitHub, Drive, Notion, and local files.

💎 Hidden gem★ 115 stars⑂ 21 forksMITupdated 2026-07
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
// project facts

Project facts

GitHub stars
115
Forks
21
License
MIT
Last updated on GitHub
26 July 2026
Listing
Hidden gem — a shorter page for a lesser-known project
Official site
Official site
// how it works

How it works

  1. Clone the repository

    Download the source and enter the folder.

  2. Install dependencies

    Pull the Node packages it needs.

  3. Connect your sources

    Link GitHub, Drive, Notion, or local folders.

  4. Search with citations

    Ask questions and get sourced answers.

// features

Why people love it

Multi-source search

GitHub, Drive, Notion, local files, and web.

Cited answers

Every answer links back to its sources.

Self-hosted

Your documents stay on your infrastructure.

Embeddings based

Semantic search over your content.

TypeScript stack

Modern codebase to extend.

Team ready

Shared search for people and agents.

Advertisement
// run it

Run it yourself

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/joungminsung/OpenDocuments.git
    cd OpenDocuments
  2. Step 2 — Install dependencies

    Pull the Node packages it needs.

    npm install
  3. Step 3 — Launch search

    Start the app after configuring sources.

    npm run dev
// use cases

What you can build

  • Search company docs with cited AI answers.
  • Query a GitHub org’s repos in plain language.
  • Unify Drive and Notion search in one box.
  • Give agents a grounded document layer.
Advertisement
// faq

Questions, answered

Who maintains OpenDocuments?

It is an open-source project at joungminsung/OpenDocuments with 21 forks.

Is it free for commercial use?

Yes. It is MIT licensed.

Which sources can it search?

GitHub, Notion, Google Drive, local files, and web sources.

Do answers include citations?

Yes. Citations back to source documents are a core feature.

Do I self-host it?

Yes. It is designed as a self-hosted RAG platform.

// keep exploring

Similar tools

AI Chat

ObsidianRAG

Ask questions of your Obsidian notes with private, local AI RAG.

★ 123 starsMIT
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

Local_Pdf_Chat_RAG

Transparent Python RAG reference with FAISS + BM25 hybrid retrieval.

★ 957 starsMIT
View guide →
RAG & Knowledge

uteke

Self-hosted rag & knowledge: 🧠 the brain for your ai — local-first memory engine for.

★ 268 starsApache-2.0
View guide →
RAG & Knowledge

docs-mcp

Self-hosted rag & knowledge: cometchat docs search + implementation bundles: add cha.

★ 97 starsApache-2.0
View guide →
RAG & Knowledge

swirl-search

Federated AI search and RAG across 100+ apps — answers with sources, without moving your data

★ 3.0k starsApache-2.0
View guide →
// alternatives

Alternatives in RAG & Knowledge

The most-starred other RAG & Knowledge projects in the LibreAI catalogue — the realistic shortlist if OpenDocuments is not the right fit.

  • MarkItDown★ 193.5k

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

  • Dify★ 157.8k

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

  • ragflow★ 91.6k

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

  • PaddleOCR★ 90.8k

    Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages

  • MinerU★ 82.5k

    MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms

// more in rag

More in RAG & Knowledge

Nearby RAG & Knowledge projects in the catalogue, closest in stars to OpenDocuments — keep exploring the shelf either side of it.

  • gno★ 115

    Local AI-driven document search and editing with first-in-class hybrid retrieval

  • dstoolkit-text2sql-and-imageprocessing★ 105

    Open rag & knowledge for this repo accelerates development of rag applications w.

  • compdfkit-conversion-sdk-mac★ 115

    High-performance PDF conversion library for macOS apps.

  • textbook-to-note★ 104

    Self-hosted rag & knowledge: turn your own pdf textbooks into an ai-searchable knowl.

  • backstage-plugin-qeta★ 116

    Internal Q&A and knowledge base for Backstage.

  • autonomie★ 103

    Open rag & knowledge for "autonomie" is a highly semantic, responsive, accessibl.

Get OpenDocuments

Free and open — grab the source, star the repo, and start creating.