My Setup
My current AI setup
The exact set of tools I use day to day, what each one is for, and what I would change. Updated whenever something moves.
THIS CHANGES OFTEN.
The stack
- V Vultr
- H Hermes
- CC Claude Code
- Ol Ollama
This setup isn't perfect, but it works well for me right now. I update this page as things change.
This changes often. That is the point of writing it down: most setup posts describe a finished state that never existed, and this one is deliberately a snapshot.
Why these four
They divide the work cleanly, which matters more than any individual tool being the best available.
The server is the boring foundation. It costs a few dollars, it never turns off, and everything that needs to keep running lives there.
The agent handles scheduled and repetitive work. It is not clever. It is reliable, which I have come to value more.
Claude Code handles anything involving real files and real complexity, including this website.
Ollama handles anything I would rather not send anywhere: drafts, notes, half-finished thinking.
What it costs
Around $30 a month, and the split surprises people: the server is the small part. Almost all of it is model usage, which varies with how much the agent actually does.
The local models cost nothing beyond electricity, which is a real reason to use them for routine work.
What I would change
The memory setup is the weak part. It works, but it is more manual than it should be, and I have not found an arrangement I am happy with yet.
I would also like fewer moving pieces. Every tool here earns its place today, but four things is three more than one thing, and each one is something that can break while I am not looking.
What I would not change
The server. It is the least interesting item on the list and the one that made everything else possible.