LearnAIWithMe

LearnAIWithMe

I Took Claude Code & NotebookLM Fully Offline

I run Claude Code and a local NotebookLM on a Mac Mini, fully offline. Both run on open source models, and nobody can pull them.

Gencay's avatar
Gencay
Jun 26, 2026
∙ Paid

Claude Fable 5 was the best model I had ever used. It lasted four days.

Then the government pulled it, and it is still gone.

That left everyone with the same thought.

What if the model we build our work on, sometimes our living, gets taken the same way?

A government can pull it, a vendor can shut it down, or the price triples overnight.

Everyone agrees we need a plan B. Mine started with a Mac Mini.

I bought it to run my Hermes agent in an isolated environment, so I asked a simple question.

What if the agent needed no frontier model at all?

I have two favorite tools, Claude Code and NotebookLM. If I could run both of them on open source models, on my own machine, the cloud could not touch them.

So I built the system. Now they cannot take my AI away.

What will we build?

I run two favorite tools on my own machine, and neither one needs a frontier model behind it.

Claude Code pointed at a local model instead of the cloud. It still writes code and builds apps, it just runs on my desk now.

Claude Code running on a local Gemma 4 model, the first half of a Claude Code and NotebookLM offline setup
Claude Code launched on Gemma 4 through Ollama, billed at $0, the start of running Claude Code and NotebookLM fully offline.

And I even created a website, using it, for $0.

SaaS trading-bot landing page built by Claude Code on a local model for free
A full landing page, Claude Code built on a local model, for $0.

NotebookLM was swapped for a local open source version. It turns my sources into a podcast and answers my questions, all offline, and my data stays safe.

I even created two different notebooks about Stoic philosophy and cortisol, the stress hormone.

Two Open Notebook notebooks on Stoicism and cortisol, a local NotebookLM alternative running offline
Two notebooks in Open Notebook, the local NotebookLM alternative.

Underneath both sits one engine, Ollama, running Gemma 4 on a Mac Mini with 16 GB. It can run millions of tokens, and it still costs me $0.

Ollama running an open source model locally on a Mac Mini
Ollama is the engine that runs Gemma 4 on the Mac Mini.

That is the whole stack: a small box, an open model, and two tools that owe nothing to a subscription.

Optional

To go fully off-grid, I connected it to my EcoFlow, a solar-powered battery station, making the whole system completely independent.

Mac Mini connected to an EcoFlow solar battery for a fully off-grid local AI agent
The Mac Mini on solar, fully off-grid.

The trick that keeps it yours

Months ago, I bought a Mac Mini and quietly moved my work onto local models, while renting my whole stack from one company started to feel like a bad bet.

Then Fable 5 died in ninety minutes, and everyone felt that the bet went bad at once.

Now the hardware is drying up. The 512 GB Mac Studio that runs a serious model is gone; only the 96 GB versions are left.

Peter Steinberger post that high-memory Mac Studios for local models are sold out
Steinberger, creator of OpenClaw, on the Mac Studio shortage.

When the person who builds OpenClaw says they cannot make these anymore, you listen.

The people who waited are buying scarce machines at a markup, learning this under pressure.

I am not in that line. My agent already runs on my desk, and I will show you exactly how I did it.

What is after the paywall?

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2026 Gencay I · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture