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 OpenCode on a private AI box
License: MIT
A terminal-native AI coding agent that reads your repo, edits files, and runs commands — pointed at a model on your own box, not a cloud API.
What it is
- An open-source CLI coding agent that works across your codebase from the terminal.
- Model-agnostic: it drives whichever model you configure.
- The coding agent BrainOutput devices ship with, tailored by us.
OpenCode is an independent project. BrainOutput has no affiliation, endorsement, or partnership with it — we sell the private hardware you can run it on. Project: OpenCode.
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
OpenCode lets you add a custom provider with an explicit base URL, or use a local runtime.
- Configure a provider whose baseURL is your box's OpenAI-compatible endpoint.
- Point it at a strong local coder model — your source never leaves the machine.
How BrainOutput fits
- Every device we sell ships with OpenCode pre-wired to the local model stack.
- Our LLM Factory can fine-tune the coder model on your own codebase and deliver it into the same setup.
Frequently asked questions
- Does my code get sent to a cloud?
- No. Pointed at your box, OpenCode reads and edits your repository against a local model — nothing leaves the machine.
- Which repo should I use?
- Use the maintained OpenCode repository (github.com/anomalyco/opencode); an older same-named repo is stale. We wire the current one on our devices.
- Can you tailor the coder model to us?
- Yes — LLM Factory fine-tunes an open-weight coder model on your codebase and ships it into the OpenCode setup 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.