joungminsung

Self-hosted open-source RAG platform that unifies organizational documents and answers natural language queries with AI

18
3
100% credibility
Found Mar 28, 2026 at 18 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

OpenDocuments indexes documents from local files, GitHub, Notion, and other sources into a unified search engine, enabling natural language questions with cited answers via local or cloud AI models.

How It Works

1
💡 Discover OpenDocuments

You find a tool that gathers all your scattered documents into one smart assistant.

2
🛠️ Run the setup wizard

Follow simple questions to pick your AI helper and ready everything with one go.

3
🚀 Open your chat assistant

Click to launch and see the friendly web page where you can talk to your files.

4
📁 Add your documents

Drag files or point to folders, and watch them get organized automatically.

5
💬 Ask and get answers

Type a question like 'How does login work?' and see the exact answer with links to sources.

6
🔗 Connect team sources

Link shared drives or online notes so everyone asks the same smart assistant.

Knowledge unlocked

Now your whole team chats naturally with all documents, saving hours of searching.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 18 to 18 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is OpenDocuments?

OpenDocuments is a self-hosted open-source RAG platform built in TypeScript that unifies scattered organizational documents from GitHub repos, Notion pages, Google Drive, Confluence, and local files into a single searchable index. It answers natural language queries with AI-generated responses and source citations, running fully offline via Ollama or with cloud LLMs like Claude or GPT. Install via npm CLI, index docs with `opendocuments index ./docs`, and query via web UI at localhost:3000 or `opendocuments ask "deployment process?"`.

Why is it gaining traction?

Stands out as a self-hosted open source AI chat server with cross-lingual search for English/Korean docs, query decomposition for complex questions, and RAG profiles (fast/balanced/precise) that balance speed vs accuracy. Docker Compose deploys everything locally – no data leaves your network – and it integrates as a knowledge base for Cursor or Claude Code via MCP. Plugins extend parsers for PDF/DOCX/code and connectors for GitHub/Notion, making it a flexible self-hosted GitHub alternative for docs.

Who should use this?

Engineering teams tired of hunting GitHub READMEs, Wikis, and Swagger specs for auth flows or API details. Product managers comparing v2 vs v3 specs across Notion and Drive. Ops/HR needing a self-hosted open source Notion alternative to query policies, budgets, or onboarding guides without SaaS costs.

Verdict

Grab it if you need a self-hosted open source LLM RAG setup now – CLI and docs are polished, features like confidence scoring and PII redaction impress despite 18 stars and 1.0% credibility score. Early-stage but MIT-licensed and Docker-ready; contribute to boost maturity.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.