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 AnythingLLM on a private AI box
License: MIT
An all-in-one app that turns your documents into private, cited chat — retrieval-augmented, workspace-organised, fully self-hostable.
What it is
- A document-to-chat workspace: drop in files and query them with citations.
- Built-in RAG, multiple workspaces, and role-based access.
- Runs as a desktop app or self-hosted Docker service.
AnythingLLM is an independent project. BrainOutput has no affiliation, endorsement, or partnership with it — we sell the private hardware you can run it on. Project: AnythingLLM.
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
AnythingLLM has a "Generic OpenAI" LLM provider for any OpenAI-compatible server.
- Choose the Generic OpenAI (or LocalAI) provider and enter your box's base URL.
- Set the model name — your documents are then embedded and queried entirely on your hardware.
How BrainOutput fits
- We provide the device plus an embedding + chat model stack sized for your corpus.
- Your document index and vectors stay on the box, never in a cloud.
Frequently asked questions
- Do my documents leave my network?
- No. With AnythingLLM pointed at your box, both embedding and inference happen locally — the corpus never leaves your premises.
- Is it really MIT-licensed?
- Yes — AnythingLLM is published under the MIT license, verified against its repository.
- How big a knowledge base can it handle?
- That depends on the model and memory; we size the device (and the embedding model) to your corpus during the assessment.
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.