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 Dify on a private AI box
License: source-available (not OSI)
A visual LLMOps platform for building agents and RAG applications — backed by a model on your own box.
What it is
- A platform to design, test, and deploy LLM apps and agents visually.
- Built-in RAG, prompt orchestration, and app APIs.
- Self-hostable for private deployments.
Dify ships under the Dify Open Source License — an Apache-based source-available license with restrictions, not a plain OSI-approved license. We label it accurately.
Dify is an independent project. BrainOutput has no affiliation, endorsement, or partnership with it — we sell the private hardware you can run it on. Project: Dify.
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
Dify supports an "OpenAI-API-compatible" model provider you configure with a base URL.
- Add the OpenAI-API-compatible provider with your box's base URL and model name.
- Build agents and RAG apps that call your private model.
How BrainOutput fits
- We deliver the device and the model endpoint Dify's apps run against.
- Your app logic, data, and inference stay on-premise.
Frequently asked questions
- Is Dify open source?
- It is source-available under the Dify Open Source License (Apache-based, with restrictions), not a plain OSI-approved license. We label it accurately.
- Can its apps use a local model?
- Yes — add the OpenAI-API-compatible provider pointing at your box and your apps call the private model.
- Good for RAG?
- Yes — Dify has built-in retrieval; pointed at your box, the whole pipeline stays private.
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.