Runs on a private AI box you own
One compact GB10-class device — 128 GB unified memory — runs it on-premise, sold and provisioned by us. No cloud API keys, no data leaving the building.
Run n8n on a private AI box
License: source-available (Sustainable Use License)
A visual automation platform with native AI nodes — wire your model into workflows across hundreds of apps, all pointed at your own box.
What it is
- A node-based automation builder with 400+ integrations.
- Native AI and agent nodes for LLM-driven steps.
- Self-hostable, so workflows and credentials stay on your infrastructure.
n8n is source-available under the Sustainable Use License, not an OSI-approved open-source license. We label it accurately rather than calling it "open source".
n8n is an independent project. BrainOutput has no affiliation, endorsement, or partnership with it — we sell the private hardware you can run it on. Project: n8n.
Cloud API keys vs your private box
The tool is the same either way. What changes is where your prompts and files go, and how you pay.
| Cloud API keys | Your private box | |
|---|---|---|
| Data location | Prompts and files are sent to a third-party API | Everything stays on hardware in your office |
| Cost model | Metered per token — scales with usage, indefinitely | A fixed hardware cost — local inference is unmetered |
| Availability | Vendor uptime, rate limits, and model retirements apply | Runs offline; you control uptime and model versions |
| EU compliance | Data-transfer and processor terms to manage per vendor | EU hardware on your premises — sovereignty is physical, not contractual |
| Model choice | Whatever the vendor exposes | Any open-weight model that fits the box — swap freely |
Indicative hardware start prices are €3 650,22 HT (ASUS) / €4 328,25 HT (Dell); the full sovereign setup is sur devis.
How it connects to your box
n8n's OpenAI / OpenAI Chat Model nodes accept a custom Base URL in the credential.
- In the OpenAI credential, set the Base URL to your box's OpenAI-compatible endpoint.
- Use that credential in AI nodes — workflow steps then call your private model.
How BrainOutput fits
- We supply the device and the local model n8n's AI nodes point at.
- Your automations run against on-premise inference — no per-token cloud bill.
Frequently asked questions
- Is n8n open source?
- It is source-available under the Sustainable Use License, which is not OSI-approved. We say so plainly instead of labelling it open source.
- Can workflows call a local model?
- Yes — set the OpenAI node's Base URL to your box's endpoint and AI steps run on local inference.
- Do credentials leave my server?
- Self-hosted n8n keeps workflows and credentials on your infrastructure; pointed at your box, inference is local too.
Run it on a box we set up for you
We size the device, install an OpenAI-compatible model stack, and hand you the endpoint this app points at. The app stays free and yours.