# About Stefan Preu

> Who Stefan "Steve" Preu is, what he calls his role, how to say his name, where he is based and where to find his public work.
> status: draft-owner-review · updated: 2026-10-20 · source: https://bot.unbrained.dev/knowledge/about-stefan

Stefan Preu, who goes by Steve, is an agentic systems architect based in Austria. He builds tools and systems that help humans and AI agents work with durable context. His main open-source project is PM CLI.

## Name, nickname and pronunciation

Stefan Preu goes by Steve, which is short for Stefan. Steve is the name on his GitHub profile and on X (@StevePreu), so "Steve Preu" and "Stefan Preu" are the same person.

"Preu" is German and is pronounced /pʁɔɪ̯/, like the German word "treu". For English speakers, "proy" (rhymes with "boy" or "joy") is a good approximation. The spelling stays Preu. Source: https://preu.at/about

## Role and focus

Stefan's chosen professional title is agentic systems architect. As he describes it, he designs the systems around AI agents: what they know when a session starts, which tools they can use, where the boundaries are, and how anyone can tell the work is done. The models come from the labs; the system around them is the part he works on.

His areas of interest include custom agent harnesses, memory and context systems, workflow design, deterministic workflows and helping organizations prepare for agentic work. He is also interested in research and in experiments with recursive language-model systems. These are areas he wants to work on, not a claim of expertise in every subfield.

## Unbrained, unbraind and the two websites

Stefan's public brand is Unbrained, spelled with an "e". His GitHub handle is unbraind, without the "e", and his npm account is unbrained.

Two websites represent the same person and overlapping work: https://preu.at is his personal professional site, and https://unbrained.dev is the services-facing entry point for client projects. Stefan launched the first versions of both on 19 October 2026. bot.unbrained.dev, where this AI representative runs, belongs to the same family.

## Location and languages

Stefan is based in Austria, in the state of Lower Austria. His CV describes German as his native language and English as business fluent.

## Open to roles, consulting and collaborations

Stefan is open to engineering roles, consulting projects and collaborations, and he gives hiring and consulting equal weight. He is also open to leadership opportunities, with the role and scope discussed individually.

This describes his interests, not his current availability. For a concrete opportunity, contact him directly through https://preu.at/contact or at stefan@preu.at.

## How he presents himself

Stefan wants to come across as curious, candid and a little playful. He calls the tone "benevolent mischief": friendly, well-intentioned and slightly quirky. He values being open to ideas, owning mistakes and saying so when he does not know something.

He prefers that people judge his work through inspectable projects and concrete examples rather than broad claims, and that his experience is described at the scope where it has actually been shown. He has said plainly that he is not a machine-learning or reinforcement-learning researcher.

## Visual style

Stefan's preferred visual direction is red, black and white, with a bold composition and subtle, non-overwhelming motion. His personal S/P mark is separate from PM CLI's own visual identity.

## Public profiles

These profiles belong to Stefan:

- Personal site: https://preu.at (facts and short answers: https://preu.at/about)
- Services: https://unbrained.dev
- GitHub: https://github.com/unbraind
- npm: https://www.npmjs.com/~unbrained
- LinkedIn: https://www.linkedin.com/in/stefanpreu/
- X: https://x.com/StevePreu
- PM CLI documentation: https://pm-cli.unbrained.dev