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 Paperclip on a private AI box
License: MIT
A control plane for running teams of AI agents — configured to drive a model on your own box rather than a metered cloud API.
What it is
- An open-source platform to coordinate multiple AI agents on tasks.
- A Node + React control plane you self-host.
- Provider-agnostic model configuration.
This is the AI project paperclipai/paperclip — not the long-standing Ruby "Paperclip" file-attachment gem of the same name.
Paperclip is an independent project. BrainOutput has no affiliation, endorsement, or partnership with it — we sell the private hardware you can run it on. Project: Paperclip.
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
Paperclip's model configuration is provider-agnostic; you can set an OpenAI-compatible endpoint. Confirm the depth of local-model support for your workflow before relying on it in production.
- Point the model configuration at your box's OpenAI-compatible endpoint.
- We validate the specific local-model setup with you during the assessment.
How BrainOutput fits
- We supply the device and the private model endpoint the agents run against.
- Orchestration and data stay on hardware you own.
Frequently asked questions
- Is this the Ruby Paperclip gem?
- No — this is the AI agent-orchestration project (paperclipai/paperclip), unrelated to the Ruby file-attachment gem of the same name.
- Can it use a fully local model?
- Its model config is provider-agnostic and accepts an OpenAI-compatible endpoint; we validate the exact local-model depth for your use case in the assessment rather than over-promising it here.
- License?
- MIT, 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.