Founder and principal investigator at ZenSation AI, an independent research lab in Kiel, Germany, working on cognitive architectures for AI, agent memory and AI safety. Self-funded, without external grants or investors — income from pilots and consulting goes back into the research.

I have been putting software into production since 2009, across three domains: financial trading systems, enterprise CRM, and now AI research infrastructure.

zenbrain — a seven-layer, neuroscience-derived memory architecture for LLM agents. Zero-dependency TypeScript, Apache-2.0. On LongMemEval-500 it wins all nine head-to-head answer-quality comparisons against Letta, Mem0 and A-Mem (three competitors × three LLM judges, Bonferroni-corrected), reaching 91.3% of a full-context oracle's binary-judge accuracy at 1/106th of the per-query token cost.

zenai — the self-hosted AI platform ZenBrain was extracted from, published as a frozen, readable snapshot.

Every number I publish is meant to be re-derived, not believed. Benchmarks ship with the protocol, the effect sizes, and the cases where the system loses. Replications and counter-results are welcome — open an issue or write.