A private AI appliance that runs entirely on hardware you own

machines

1

external API calls

0

data leaving the device

0

automations, always on

3

Some work should not leave your control, and the usual response is to accept a weaker product in exchange for that. This is what I built to find out how much of a compromise it actually is.

A single machine runs open models locally, with no external API and no data leaving the device. On top of it sits a set of always-on automations: inbox triage, a scheduled daily briefing, and, until I retired it in October 2026, retrieval-augmented answering over a private knowledge base.

How it is built

The design separates a planner from the workers. A lightweight brain decides what should run and when. The local inference server and a handful of small, single-purpose applications do the work, scheduled by the operating system and stored locally.

• Local inference for open weights, served on-device.
• A private retrieval index over my own documents, so answers come from my material rather than from the general internet. Retired in October 2026.
• Scheduled automations that run unattended and report in.

Why it is here

It is the evidence behind a position I take with clients: the private end of the deployment curve is not a penalty box. With current open weights and a disciplined architecture, an organization gets real daily leverage from AI while keeping sensitive data on infrastructure it owns outright. Until October 2026 this appliance also served the private retrieval corpus behind the rest of the estate, so the claim was load-bearing rather than illustrative.