Reasoning intelligence · no cloud dependence · yours

Intelligence should accumulate where it's earned — and stay owned by whoever earned it.

A reasoning mind that runs on your hardware, with no dependence on a cloud AI. HKOS makes that reasoning intelligence yours.
Intelligence sovereignty — a reasoning mind that's genuinely yours. Verified reasoning for work that has to be right. Your data. Your hardware. Your mind. One backbone — the law office, the clinic, the farm.
80k+
captures in the brain — growing since late March 2026
3
small loops — a pilot tank, an established colony, a robot in calibration — one shared memory
100%
owned at the edge — your data never leaves to train someone else's model
1
architecture, domain-agnostic — soil, hives, a classroom, a practice
The thing that's broken

Every conversation with an AI starts from zero. The context you built last week is gone, and whatever it learned about your domain went to a model you don't own.

1

Memory doesn't compound. A tool that forgets can't get better at your problem. It stays a generalist forever, and you re-explain yourself forever.

2

The value flows the wrong way. The understanding you generate becomes training data for someone else's product — extracted upward, not accumulated where you stand.

3

Expertise stays trapped. The person who knows how the system actually runs can't hand that knowledge to anyone — it walks out the door when they do.

The claim, in three parts

Sovereignty isn't a feature. It's the architecture.

Not "an AI that remembers" — every product says that. Something more specific: a system designed so that perspective on a domain becomes an asset, owned where it's generated, and transferable without being given away.

01Scoped

A brain for a domain, not a memory dump. Project-scoped

A sovereign brain isn't one giant pile of everything. It's a protégé assigned to a perspective — this aquaponics system, this apiary, this curriculum — that learns under that lens and gets sharper at exactly one thing. Cross-domain search still works when you want it. One substrate, many specialists.

02Owned

It lives at the edge, and so does its memory. Edge-resident

A small model in a grow tent holds the local view of its own project and writes to a brain you control. The most sensitive material never embeds externally at all. The architecture follows the work; the data stays where it was earned. Escalating to a bigger model is a choice, not a default surrender.

03Mature

The goal is mediation, not storage. Mature

A brain that stores notes is a database. A brain that's mature enough to brief a collaborator, draft a reply, and hold context across weeks on the project's behalf is the actual deliverable. Storage is the seed. Mediation is the harvest. And a mature brain can teach a peer brain the pattern — without handing over what it knows.

The proof — not a slide

The brain is running. You can watch it.

The claim above is easy to make and hard to believe. So it's being built in the open. Node Zero is a cold-water aquaponics pilot in a New England basement — a 30-gallon tank, goldfish and parsley, running while the sensor stack gets hard-soldered on the bench; the instrumented 120+ gallon build moves into the garage in September. The brain behind it is already live: ~80,000 captures, growing since late March 2026.

i. It's honest, not modeled.

The Live page is wired to the real API and shows exactly what the system reports — including an honest offline state until the tank sensors come online. No projections, no invented numbers.

ii. Every capture is a training example.

The dataset isn't a byproduct. It's the point. The longer the brain runs, the smarter the system that runs on it gets — accumulation made literal.

iii. The method is documented.

The operations manual outline is public, and the full manual is being ported section by section. Replicable on purpose — that's how you prove a pattern.

iv. The brain is real infrastructure.

Build notes, decisions, session captures — all in one queryable memory that decides what's worth surfacing tomorrow. The substrate, working at the smallest honest scale.

The memory, observed

Everything writes to one brain. This is it, live.

Every capture — a note, a decision, and soon a sensor reading — becomes a node in one growing memory. This is that memory, live — each point a capture, each line a relationship the brain drew on its own. Locked nodes stay locked: the shape crosses the wire, the contents never leave the box.

brain.killercatfish.com / mind · live · contents stay home

Here's my brain. What's yours look like?

Why it's domain-agnostic

One node became a method. The method doesn't care what the domain is.

Node Zero is proving the shape: a small loop → a scoped brain → memory that compounds → a documented, transferable pattern. Nothing about that shape is specific to fish. Swap the inputs and the same architecture runs a different domain. Each new node is a peer, running the same playbook somewhere else.

Node 0

Aquaponics

Pilot

Cold-water pilot, basement. A 30-gallon tank — goldfish and parsley — while the sensor stack is soldered on the bench. The 120+ gallon instrumented build lands in September.

Node 1

The Apiary

Sensing: winter build

The colony is established and working; the brain that watches it is a winter build.

Node 2

The Raised Bed

Calibrating

A FarmBot bed — built, working through track calibration. Soil as a domain — same architecture, different inputs.

Node n

Yours

The pattern

A classroom, a practice, a workshop, a farm. If you care about a domain, it can have a brain.

And here's how things get in

A brain is only as good as what reaches it. The same architecture takes input from wherever you already are — the point isn't the sensor, it's that heterogeneous streams land in one memory and get reasoned over together.

// SENSORS
The physical loop

pH, temp, dissolved oxygen, soil moisture — a Pi on the loop, writing to the brain. The Node Zero pattern; the stack is on the bench now.

// WEARABLE
Mentra · in dev

An AR/wearable stream joining the same loop — a vivid, sensor-rich feed that proves heterogeneous inputs reason together, not just side by side.

// CAPTURE
Phone & desktop

A note, a decision, a photo — typed or dictated from where you work. Lands at home, typed and deduplicated on the way in.

// AGENT
From your AI chats

Conclusions worth keeping get captured straight from a working session into the brain — so the next conversation doesn't start from zero.

The working record

This gets built in public. The notebook is where it actually happens.

Field notes, build logs, and the occasional dinner — written while the solder is still warm. Don't take the homepage's word for any of it; read the notes.

First real measurement of the margin-conservation law on the sovereign corpus: the gap between the right memory and the best wrong one closes from 0.090 to 0.011 as the corpus grows.

The day cortex_watch went live — and routed its own evidence into the right folder.

First in a series. Half a London broil from earlier in the week, a pound of ground veal, a Dutch oven, and a Claude tab open the whole time. Notes on what worked.

Where this goes

From one basement to a network of peers.

Each node is sovereign on its own and stronger in a network. The brains trade the pattern, never the data. That's the whole bet, drawn small enough to be honest about.

Node Zero live Hive & soil nodes A product others run Peer network