BrainOutput
English

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.

ASUS Ascent GX10 — GB10-class sovereign AI device on a desk (official ASUS image)
ASUS Ascent GX10from €3 650,22 HT
Dell Pro Max with GB10 — GB10-class sovereign AI device (official Dell image)
Dell Pro Max with GB10from €4 328,25 HT

All private-AI-box apps

Run Cline on a private AI box

License: Apache-2.0

An autonomous coding agent inside VS Code that plans, edits across files, and runs commands — against a model hosted on your own box.

What it is

  • An open-source VS Code extension that takes a task and works across your project.
  • Shows its plan and diffs for approval as it goes.
  • Has a first-class "OpenAI Compatible" provider for local endpoints.

Cline is an independent project. BrainOutput has no affiliation, endorsement, or partnership with it — we sell the private hardware you can run it on. Project: Cline.

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 keysYour private box
Data locationPrompts and files are sent to a third-party APIEverything stays on hardware in your office
Cost modelMetered per token — scales with usage, indefinitelyA fixed hardware cost — local inference is unmetered
AvailabilityVendor uptime, rate limits, and model retirements applyRuns offline; you control uptime and model versions
EU complianceData-transfer and processor terms to manage per vendorEU hardware on your premises — sovereignty is physical, not contractual
Model choiceWhatever the vendor exposesAny 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

Cline's API-provider list includes an "OpenAI Compatible" option (plus LM Studio / Ollama presets).

  • Select the OpenAI Compatible provider and paste your box's base URL.
  • Choose the served model — Cline then works against your private model in-editor.

How BrainOutput fits

  • We supply the device and a capable local coder model for Cline to drive.
  • Your codebase and the agent's actions stay on your own hardware.

Frequently asked questions

Can Cline run without a cloud key?
Yes — its OpenAI Compatible provider points at your box's local endpoint, so it needs no cloud key for inference.
Does it edit files on its own?
It proposes plans and diffs you approve; the approval flow keeps you in control while the model runs privately.
License?
Apache-2.0, verified against its repository.

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.