The simplest self-hosted RAG you'll ever set up (Apache 2.0, 20K stars)

#ai #docker #selfhosted #ollama

Most RAG tools make you choose between simplicity and power. MaxKB doesn't try to be powerful — it tries to be simple, and it nails it.

20K+ GitHub stars. Apache 2.0. Almost no English content. Here's the guide.

What is MaxKB?

MaxKB (Max Knowledge Base) is a knowledge base Q&A system by the 1Panel team. It connects to any OpenAI-compatible API — including Ollama — and lets you upload documents, ask questions, and embed a chat widget into any website.

That last part is the killer feature: MaxKB generates a JavaScript snippet that drops a chat widget into any HTML page. One script tag. No iframe, no backend changes needed. Apache 2.0 means you can embed this in commercial products with no restrictions.

Setup

3 commands, under 5 minutes.

Clone the repo, copy .env.example to .env, then docker compose up -d. Open localhost:8081 → admin / admin123 → Settings → Model Provider → Ollama → http://ollama:11434.

Create a knowledge base, upload a PDF, start asking questions. That's the entire setup.

Full docker-compose: maxkb-english-guide

Embed Widget

MaxKB generates a JavaScript snippet — drop it into any HTML page and a chat widget appears bottom-right. No iframe, no backend changes. This is what makes MaxKB unique among RAG tools: it's designed to be embedded.

Go to: Application → your app → Embed → copy the script tag → paste into any HTML page.

API

Works from Python, JavaScript, curl, n8n — anything that speaks HTTP. POST your question to /api/application/{app_id}/chat/completions with a Bearer token. Returns {"content": "the answer"}.

Full Python + JavaScript examples in the repo.

MaxKB vs the Alternatives

	MaxKB	WeKnora	FastGPT	RAGFlow
Setup time	⚡ 3 min	5 min	10 min	15 min
License	Apache 2.0	MIT	Custom*	Apache 2.0
Embed widget	✅	❌	❌	❌
Autonomous agent	❌	✅	✅	❌
PDF table parsing	Basic	Basic	Good	Excellent
Commercial embed	✅	✅	❌	✅