RAGFlow
ActiveRAG engine with deep document parsing (OCR, layout and tables) and cited answers.
- ★ 92.6k
- ⟳ Oct 22, 2026
- Permissive
- rec. 16 GB RAM
- from €69.99/mo
Upload company documents and let staff or customers ask questions with cited answers.
We track 6 self-hostable knowledge base & rag apps: RAGFlow, AnythingLLM, PrivateGPT, Onyx (formerly Danswer), FastGPT, MaxKB. Most GitHub stars: RAGFlow (92.6k). Lowest official hardware: AnythingLLM (minimum 2 vCPU · 2 GB RAM · 5 GB disk), from about €19.99/month on our reference server.
Last updated
| App | License | Official hardware | Est. server cost | GitHub stars | Status |
|---|---|---|---|---|---|
| RAGFlow | Apache-2.0 (Permissive) | recommended 4 vCPU · 16 GB RAM · 50 GB disk (no separate minimum published) | from €69.99/mo | 92.6k | Active |
| AnythingLLM | MIT (Permissive) | minimum 2 vCPU · 2 GB RAM · 5 GB disk | from €19.99/mo | 67.4k | Active |
| PrivateGPT | Apache-2.0 (Permissive) | Not published | Not estimated (no official RAM figure) | 57.6k | Active |
| Onyx (formerly Danswer) | MIT (Community Edition) + Onyx Enterprise License (ee directories) (Open core) | minimum 4 vCPU · 10 GB RAM · 32 GB disk (recommended 8 vCPU · 16 GB RAM · 500 GB disk) | from €69.99/mo | 32.8k | Active |
| FastGPT | FastGPT Open Source License (Apache-2.0 with conditions) (Custom / conditional) | minimum 2 vCPU · 4 GB RAM (recommended 2 vCPU · 8 GB RAM) | from €19.99/mo | 29.9k | Active |
| MaxKB | GPL-3.0 (Copyleft (GPL)) | minimum 4 vCPU · 8 GB RAM · 100 GB disk | from €35.99/mo | 23.0k | Active |
RAG engine with deep document parsing (OCR, layout and tables) and cited answers.
All-in-one private chat with your documents, agents and an embeddable widget.
API-first private document Q&A that sits on top of your own LLM server.
AI chat and enterprise search connected to 50+ workplace apps.
Knowledge-base Q&A and visual AI workflow platform.
Enterprise knowledge-base and agent platform with RAG and workflows.