Onyx (formerly Danswer)
AI chat and enterprise search connected to 50+ workplace apps.
Quick answer
Onyx (formerly Danswer) is an AI chat and enterprise search connected to 50+ workplace apps, listed under Knowledge base & RAG. A typical small-business use: ask questions across Slack, shared drives and wiki pages in one place. Official hardware: minimum 4 vCPU · 10 GB RAM · 32 GB disk (recommended 8 vCPU · 16 GB RAM · 500 GB disk). That fits a Hetzner Cloud CPX42 server at about €69.99/month (server only, excl. VAT). License: MIT (Community Edition) + Onyx Enterprise License (ee directories), which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What is Onyx (formerly Danswer)?
Onyx connects to 50+ workplace applications such as Slack, indexes their knowledge, and gives staff a chat interface with search, agents and actions on top of it. A lightweight "Lite" mode works as a plain chat UI without document indexing.
Where it fits in a 10–200 person business
- Ask questions across Slack, shared drives and wiki pages in one place
- Onboarding assistant that knows internal processes
- Self-hosted alternative to enterprise search tools for data-sovereignty reasons
These use cases are our editorial suggestions, not claims made by the project.
Can a business use Onyx (formerly Danswer)? (license)
| License | MIT (Community Edition) + Onyx Enterprise License (ee directories) |
|---|---|
| Type | Open core: Core is MIT/Apache; enterprise folders need a paid license. |
| Internal business use | Allowed under the license text |
| What to watch | The Community Edition is MIT. Code in "ee" directories is under the Onyx Enterprise License. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
What hardware does Onyx (formerly Danswer) need?
| Minimum | 4 vCPU · 10 GB RAM · 32 GB disk |
|---|---|
| Recommended | 8 vCPU · 16 GB RAM · 500 GB disk |
Standard mode. Disk is 32 GB plus about 2.5x your indexed data; 500 GB is suggested for organisations under 5,000 users. Lite mode (no indexing): minimum 2 vCPU, 2 GB RAM, 10 GB disk.
How much does it cost to host Onyx (formerly Danswer) per month?
| Minimum spec | 4 vCPU · 10 GB RAM · 32 GB disk → CPX42 (8 vCPU, 16 GB, 320 GB disk) €69.99/mo |
|---|---|
| Recommended spec | 8 vCPU · 16 GB RAM · 500 GB disk → CPX42 (8 vCPU, 16 GB, 320 GB disk) €69.99/mo |
How we got this: we took the cheapest Hetzner Cloud Regular Performance (shared AMD vCPU) plan with at least the RAM and vCPU the project lists, using prices read from www.hetzner.com/cloud/regular-performance on 2026-10-22. "From" monthly price cap shown by Hetzner, excluding VAT. Prices vary by location. Covers the server only; it excludes LLM API usage, backups, extra storage, GPUs and your time. Disk is not matched; add a volume if you need more than the plan includes.
How to deploy Onyx (formerly Danswer)
Method: Install script (Docker Compose)
curl -fsSL https://onyx.app/install_onyx.sh | bashFrom the official instructions: github.com/onyx-dot-app/onyx#readme. Always check the source for the current version before you run it.
Known gotchas when self-hosting Onyx (formerly Danswer)
Alternatives in Knowledge base & RAG
- RAGFlow RAG engine with deep document parsing (OCR, layout and tables) and cited answers. Compare Onyx (formerly Danswer) vs RAGFlow
- AnythingLLM All-in-one private chat with your documents, agents and an embeddable widget. Compare AnythingLLM vs Onyx (formerly Danswer)
- PrivateGPT API-first private document Q&A that sits on top of your own LLM server. Compare Onyx (formerly Danswer) vs PrivateGPT
- FastGPT Knowledge-base Q&A and visual AI workflow platform. Compare FastGPT vs Onyx (formerly Danswer)
- MaxKB Enterprise knowledge-base and agent platform with RAG and workflows. Compare MaxKB vs Onyx (formerly Danswer)
Onyx (formerly Danswer) FAQ
How much RAM does Onyx (formerly Danswer) need?
The official minimum is 4 vCPU · 10 GB RAM · 32 GB disk. The recommended spec is 8 vCPU · 16 GB RAM · 500 GB disk. Standard mode. Disk is 32 GB plus about 2.5x your indexed data; 500 GB is suggested for organisations under 5,000 users. Lite mode (no indexing): minimum 2 vCPU, 2 GB RAM, 10 GB disk.
How much does it cost to self-host Onyx (formerly Danswer)?
The software is free to download. Based on the official minimum 4 vCPU · 10 GB RAM · 32 GB disk (recommended 8 vCPU · 16 GB RAM · 500 GB disk): That fits a Hetzner Cloud CPX42 server at about €69.99/month (server only, excl. VAT). That covers the server only, not LLM API usage, backups, extra storage or your time.
Is Onyx (formerly Danswer) free for commercial use?
Onyx (formerly Danswer) is licensed under MIT (Community Edition) + Onyx Enterprise License (ee directories) (Open core). Internal business use is allowed under the license text. The Community Edition is MIT. Code in "ee" directories is under the Onyx Enterprise License. This is a summary, not legal advice.
What are common problems when self-hosting Onyx (formerly Danswer)?
OpenSearch puts indices into read-only mode at 95% disk usage, which blocks all writes. Monitor disk space. Lite mode needs under 1 GB of memory but cannot index documents.
Is Onyx (formerly Danswer) still maintained?
Yes, it is actively developed. Last commit: Oct 22, 2026. Latest release: v4.9.2 (Oct 15, 2026). Checked Oct 22, 2026.
How do I install Onyx (formerly Danswer)?
The official method is Install script (Docker Compose). The exact commands are in the "How to deploy" section above and in the official instructions: https://github.com/onyx-dot-app/onyx#readme
What are self-hosted alternatives to Onyx (formerly Danswer)?
Other apps in Knowledge base & RAG: RAGFlow, AnythingLLM, PrivateGPT, FastGPT, MaxKB.
Sources
- GitHub repository: github.com/onyx-dot-app/onyx
- Official documentation, Hardware requirements, Gotcha 1: docs.onyx.app/deployment/getting_started/resourcing
- License text: github.com/onyx-dot-app/onyx/blob/main/LICENSE
- Deploy instructions, Gotcha 2: github.com/onyx-dot-app/onyx#readme
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-22. Spotted something out of date? Tell us.