VertexPaceLocal AI Philosophy
SovereignSovereignFully self-contained and under your control. A sovereign AI runs on your hardware with no external services, no corporate logging, and no policy changes you didn't agree to. intelligence

BABY AI

Private, sovereignSovereignFully self-contained and under your control. A sovereign AI runs on your hardware with no external services, no corporate logging, and no policy changes you didn't agree to. AI that runs entirely on your hardware. From a private desktop chat app to a swarm of zero-dependency specialist binariesSpecialist binariesTiny compiled programs — typically 35 KB — each built for one specific domain (first aid, pool chemistry, HVAC). No model weights, no internet, no subscription. that fit in 50 KB. No cloud, no logs, no compromise.

Why local

Cloud AI is a liability.

You don't own the policy

Every message you send to a cloud AI service lives on someone else's servers. Privacy policies change. "We don't train on your data" covers today, not next quarter.

Open models, your hardware

Built on an open local AI runtimeLocal AI runtimeA local engine that runs open AI language models entirely on your Mac — no cloud connection, no account. Baby AI Lite uses it under the hood. — the same class of engine indie devs use for local AI. Bring any model you want. Swap them anytime.

Verifiable, not a promise

Unplug your Wi-Fi mid-conversation. The app keeps working. That's the only privacy proof that matters.

Architecture — Baby AI v2

Four planes, one pipeline

Baby AI v2 runs a four-step cognitive loop — the same sequence a biological brain uses. Not an LLM wrapper. Not a rules engine. A compact, auditable loop written in Light Code that you can read in full. Each plane operates on the same 64-byte concept grid.

Predict

Generates an expectation before acting. Weights update from past outcomes. Outputs a confidence score the Decide plane reads. Running in v2 today.

Decide

Seven-step loop on 64 bytes. Reads the PREDICT confidence map and picks an action with traceable reasoning. Verified and running.

Create

Generates the actual response using recursive slot machines seeded from memory and PREDICT output. Personalised from prior lessons. Spec complete — building now.

Learn

Observes every outcome and refines all three planes. Written in Light Code. Persists learned patterns to sovereign memory, tagged by concept byte.

Baby AI vs NovaGlyph

Two sides of the same coin

Both are built from Light Code — the same small symbolic language. What they do with it is opposite.

Chat app

Baby AI

Reasons through Light Code's planes, then hands off to a local AI model to generate the actual reply. Every answer is written fresh.

Talks. Writes a new answer every time.
Can improvise — which also means it can be wrong.
Compiler

NovaGlyph

Compiles the facts you write into a tiny native binary. No model runs at query time — it looks the answer up.

Doesn't talk. Looks the answer up.
Can't improvise — same fact every time, for better or worse.
Same foundation — Light Code, the 64-byte concept grid
Products

What's available today

Baby AI Lite

The flagship desktop AI chat. Runs entirely on your Mac, fully local. Your data never leaves the machine. Live now — enquire to buy.

NovaGlyph Kit v1.3.0

29 working template Baby AIs you edit, recompile, and ship. Each is one text file of facts plus a 20-line reasoning engine. ~35 KB native binary. No cloud, no model, no API key.

Master Suite — built to order

Specialist binaries compiled to your spec — auditor, vault, medic, mesh probe, contract verifier and more. ~35 KB native, every answer traceable. Order via email.

Universal Code Map — Free

Interactive explainer covering the full history of AI — from GOFAI to deep learning to Light Code's adaptive planes. Includes a live AI guide that answers questions about all three eras.

Explore the map →
Pack Forge → Baby AI Lite

See it in action

Every Baby AI starts empty. It knows nothing about your field until you — the professional — search a credible source, read the draft, and approve it. That's deliberate: building a pack takes real work, the same way writing anything worth trusting does. The payoff is what it refuses to do — it never answers from anything you haven't vouched for, and it says so when it doesn't know. Try the same pipeline below across three unrelated fields.

Loading demo…

Built by Zac Page in Sydney
© 2026 VertexPace · All Rights Reserved