Skip to content
Nick Wharton · Independence, MO

Quiet systems.
Loud results.

I build self-hosted AI, run a 22-node home cluster that thinks like one machine, and ship product end to end - from kernel to checkout.

14
online / 20 managed
136
k3s pods
1
operator

What I build

A few layers down from the dashboard.

Self-hosted AI

Local models, real workflows. Inference orchestration, retrieval, and agent runtimes that live on my own metal - not rented tokens, not vendor lock.

ollamamcpagents

Fleet operations

Twenty-two machines that behave like one. Doctrine, syncing, and shared memory across hardware that runs from a closet, not a region.

k3stailscaleobservability

Shipped product

Full-stack delivery on a tight schedule - e-commerce, internal tools, collector workflows. Whatever the business needs, one operator can ship.

reactphpmysql

Agent doctrine

Long-running systems that act on intent, not just instructions. Memory, identity, and guardrails so the next session picks up where the last stopped.

memoryhandoffguardrails

Observability

Real telemetry on real workloads. Not dashboards for show - signals that actually wake somebody up when the right thing breaks.

metricslogstraces

Hardening & ops

Backups, isolation, secrets routing, and the unglamorous work of keeping anything serious in production. The reason the rest still runs.

backupssecretsrecovery

Live proof

Five live reads, backed by public signals.

The headline is backed by real numbers: fleet health, deployed properties, current work, and backup state - the same public-safe data that powers the rest of the site.

Fleet pulsecached
14 / 20136 pods across 7 k3s nodes
Open fleet
Cluster homelive
Independence, MO22 pieces of hardware, one closet, one operator
See the room
Now shippingactive
Floating-layer rebuildGlass surfaces across every route
Timeline
Self-hosted AIwarm
S.A.M doctrineLocal models on owned metal, no cloud bill
Read the doctrine
Backupssynced
UNAS Pro · 3-2-1Snapshot 14 min ago, offsite nightly
The stack

The fleet

S.A.M - one mind, many machines.

Twenty-two pieces of hardware - workstations, servers, laptops, GPU boxes - running a shared doctrine. One operator, one source of truth, and just enough automation that the machines stay in agreement when I'm not looking.

Open fleet evidence
nick@fleet - status
S.A.M shell · fleet brief · cached
Type 'help', or try 'fleet'.

Built with Poke

This one shipped from a text thread.

Poke is the iMessage-native agent that designs and deploys these sites. I describe what I want; it builds, commits, and ships — then the same build runs in two homes: Poke’s cloud and my own fleet.

Describe it over text

Plain iMessage — no IDE, no dashboard. Poke turns intent into a real, deployable build.

Ship to one repo

Every change lands in GitHub — the single source of truth both homes build from.

Deploy to both

Poke rebuilds its cloud copy; my fleet pulls the same image. One push, two live sites.

Apps & sites

Everything ships from one desk.

Every property runs on the same fleet, shares the same auth and edge layer, and ships from the same operator desk.

Strange Music & The OG Network

Artist & family storefronts

Contact

If the work looks like your problem, get in touch.

I take on a small number of consulting engagements when the fit is right - infrastructure design, AI ops, or full-stack delivery that needs a senior pair of hands.

Start a conversation