Local-First AI

Most AI work doesn’t need a data center.

Aria is a private AI stack that runs where the data already lives. Routine work is handled by models on hardware in the building. A frontier model is called only when the task genuinely needs one, and the system decides which is which, per request.

Three tiers, cheapest capable one wins

Every request is classified before it runs. Most never leave the property. The tiers degrade gracefully in both directions: if a local tier is unreachable, the request moves up rather than failing.

Tier 0

On-box classification

A small model that decides where each request should go, plus semantic search and cheap templating. Milliseconds, no accelerator required.

Tier 1

Local inference on Apple Silicon

Large open-weight models served natively over unified memory. Conversation, drafting, summarizing, first-pass review. This tier does the bulk of the work.

Tier 2

Frontier escalation

Reserved for genuine judgment: production changes, security, anything irreversible. Certain categories are hard-routed here and never left to the classifier.

How it’s built

Local by default

Escalating off-box is a deliberate decision the system has to justify, not the default path.

Fails forward, never hangs

Every tier has a bounded timeout and a next step. An unreachable model degrades the route; it doesn’t drop the task.

Guardrails aren’t prompts

High-stakes categories are enforced at the process boundary, not requested politely in a system prompt.

Measured, not assumed

Routing decisions are logged and reviewed. If a tier isn’t earning its place, the data says so.

This is private infrastructure

Aria is personal infrastructure, not a product. There is no sign-up, no waitlist, and no public endpoint, this page is a description of the system, not a way in.