Onyx (formerly Danswer) vs RAGFlow
Short answer
Onyx (formerly Danswer): AI chat and enterprise search connected to 50+ workplace apps. RAGFlow: RAG engine with deep document parsing (OCR, layout and tables) and cited answers. Both are in our Knowledge base & RAG category.
Choose RAGFlow if you want: fewer license conditions (Permissive vs Open core) and larger community (92.6k vs 32.8k GitHub stars).
Last updated · computed from each project's official docs and live GitHub data · sources
Onyx (formerly Danswer) vs RAGFlow side by side
| Onyx (formerly Danswer) | RAGFlow | |
|---|---|---|
| Category | Knowledge base & RAG | Knowledge base & RAG |
| What it is | AI chat and enterprise search connected to 50+ workplace apps. | RAG engine with deep document parsing (OCR, layout and tables) and cited answers. |
| License | MIT (Community Edition) + Onyx Enterprise License (ee directories) | Apache-2.0 |
| License type | Open core | Permissive |
| License conditions | The Community Edition is MIT. Code in "ee" directories is under the Onyx Enterprise License. | Permissive. Internal and commercial use allowed; keep license and notices. |
| Status | Active | Active |
| GitHub stars | 32.8k | 92.6k |
| Last commit | Oct 22, 2026 | Oct 22, 2026 |
| Latest release | v4.9.2 | v1.0.0-rc2 |
| Minimum hardware | 4 vCPU · 10 GB RAM · 32 GB disk | Not published |
| Recommended hardware | 8 vCPU · 16 GB RAM · 500 GB disk | 4 vCPU · 16 GB RAM · 50 GB disk |
| RAM measured by us | Not tested yet | Not tested yet |
| GPU | Not required / not stated | Not required / not stated |
| Est. server cost | from €69.99/mo | from €69.99/mo |
| Deploy method | Install script (Docker Compose) | Docker Compose |
| Known gotchas | 2 listed | 2 listed |
| Telemetry | On by default | Not documented |
| Calls home by default | Not documented | Not documented |
| SSO (OIDC / SAML / LDAP) | Not documented | Free (OIDC free) |
| Audit log | Not documented | Not documented |
| RBAC | Paid / enterprise only | Basic free, more in paid plan |
| Details | Full Onyx (formerly Danswer) guide → | Full RAGFlow guide → |
Key differences
- License: Onyx (formerly Danswer): MIT (Community Edition) + Onyx Enterprise License (ee directories) (Open core). RAGFlow: Apache-2.0 (Permissive).
- Official hardware: Onyx (formerly Danswer): minimum 4 vCPU · 10 GB RAM · 32 GB disk (recommended 8 vCPU · 16 GB RAM · 500 GB disk). RAGFlow: recommended 4 vCPU · 16 GB RAM · 50 GB disk (no separate minimum published).
- Deploy: Onyx (formerly Danswer): Install script (Docker Compose) · multi-container stack. RAGFlow: Docker Compose · multi-container stack.
- GitHub stars: Onyx (formerly Danswer): 32.8k. RAGFlow: 92.6k.
- Latest release: Onyx (formerly Danswer): v4.9.2 (Oct 15, 2026). RAGFlow: v1.0.0-rc2 (Oct 16, 2026).
Same for both: Category: Knowledge base & RAG; GPU: not required or not stated; Est. server cost: from €69.99/mo; Status: Active; Last commit: Oct 22, 2026.
Onyx (formerly Danswer) vs RAGFlow: FAQ
Onyx (formerly Danswer) or RAGFlow: which should a small business choose?
Choose RAGFlow if you want: fewer license conditions (Permissive vs Open core) and larger community (92.6k vs 32.8k GitHub stars).
Which is cheaper to self-host, Onyx (formerly Danswer) or RAGFlow?
Onyx (formerly Danswer): from €69.99/mo. RAGFlow: from €69.99/mo. Our estimate is the cheapest Hetzner Cloud plan that meets each project's official RAM and vCPU figure; it covers the server only.
How much hardware do Onyx (formerly Danswer) and RAGFlow need?
Onyx (formerly Danswer): minimum 4 vCPU · 10 GB RAM · 32 GB disk (recommended 8 vCPU · 16 GB RAM · 500 GB disk). RAGFlow: recommended 4 vCPU · 16 GB RAM · 50 GB disk (no separate minimum published).
What is the license difference between Onyx (formerly Danswer) and RAGFlow?
Onyx (formerly Danswer): MIT (Community Edition) + Onyx Enterprise License (ee directories) (Open core). The Community Edition is MIT. Code in "ee" directories is under the Onyx Enterprise License. RAGFlow: Apache-2.0 (Permissive). Permissive. Internal and commercial use allowed; keep license and notices. This is a summary, not legal advice.
Is Onyx (formerly Danswer) or RAGFlow more actively maintained?
Onyx (formerly Danswer): Active, last commit Oct 22, 2026. RAGFlow: Active, last commit Oct 22, 2026. GitHub data refreshed Oct 22, 2026.
Which is easier to deploy, Onyx (formerly Danswer) or RAGFlow?
Onyx (formerly Danswer) installs via Install script (Docker Compose) (multi-container stack); RAGFlow via Docker Compose (multi-container stack). Onyx (formerly Danswer) lists 2 known gotchas and RAGFlow lists 2; see each app page.
Related
- Onyx (formerly Danswer) self-hosting guide · RAGFlow self-hosting guide
- All Onyx (formerly Danswer) alternatives, ranked
- All RAGFlow alternatives, ranked
- AnythingLLM vs Onyx (formerly Danswer)
- AnythingLLM vs RAGFlow
- Coze Studio vs RAGFlow
- Dify vs RAGFlow
- FastGPT vs Onyx (formerly Danswer)
- FastGPT vs RAGFlow
- Khoj vs Onyx (formerly Danswer)
- MaxKB vs Onyx (formerly Danswer)
- MaxKB vs RAGFlow
- Onyx (formerly Danswer) vs Open Notebook
- Onyx (formerly Danswer) vs PrivateGPT
- Open Notebook vs RAGFlow
- Add a third app in the interactive comparison
Sources
- Onyx (formerly Danswer) GitHub repository: github.com/onyx-dot-app/onyx
- Onyx (formerly Danswer) documentation, Onyx (formerly Danswer) hardware requirements: docs.onyx.app/deployment/getting_started/resourcing
- Onyx (formerly Danswer) license: github.com/onyx-dot-app/onyx/blob/main/LICENSE
- Onyx (formerly Danswer) deploy instructions: github.com/onyx-dot-app/onyx#readme
- RAGFlow GitHub repository: github.com/infiniflow/ragflow
- RAGFlow documentation, RAGFlow hardware requirements, RAGFlow deploy instructions: github.com/infiniflow/ragflow#-get-started
- RAGFlow license: github.com/infiniflow/ragflow/blob/main/LICENSE
- Hetzner Cloud pricing used for cost estimates (read 2026-10-22): www.hetzner.com/cloud/regular-performance
- GitHub REST API (stars, commits, releases): docs.github.com/en/rest
Every value is generated from the same verified data as the app pages. Spotted something wrong? Tell us.