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 Langflow on a private AI box
License: MIT
A visual builder for agents and RAG pipelines — pointed at a model on your own box.
What it is
- A Python-based visual builder for LLM agents and flows.
- Components for models, retrieval, tools, and memory.
- Self-hostable, MIT-licensed.
Langflow is an independent project. BrainOutput has no affiliation, endorsement, or partnership with it — we sell the private hardware you can run it on. Project: Langflow.
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
Langflow's OpenAI component exposes a base_url override (and there are Ollama/LocalAI components).
- Set the OpenAI component's base_url to your box's OpenAI-compatible endpoint.
- Assemble agents/RAG flows that run entirely on local inference.
How BrainOutput fits
- We deliver the device and the model your flows connect to.
- Everything from embeddings to generation stays on-premise.
Frequently asked questions
- Does Langflow support local models?
- Yes — override the OpenAI component's base_url (or use its Ollama/LocalAI components) to run against your box.
- License?
- MIT, verified against its repository.
- Can I move from prototype to production on the box?
- Yes — build the flow visually, then run it against the same private endpoint we provision on your device.
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.