I build systems that work.
Systems architect. Builder. Self-taught engineer.
Senior Solutions Architect at Pressable • Founder at Clapham Digital
I design distributed systems, build developer tools, and architect infrastructure at scale. At Pressable, I work on WordPress hosting infrastructure and performance. Independently, I build AI-powered cognitive infrastructure and consumer apps that teach complex skills simply.
No CS degree. I learned to build things by building things. The approach hasn't changed in 30 years: first principles over patterns, constraints as design material, and doing it right the first time because backtracking costs 3–5x what thoroughness costs upfront.
4,000+ GitHub contributions in the last year.
Systems I've designed and built.
Distributed cognitive infrastructure. Multi-AI orchestration with parallel consultation, real-time sensor pipelines, automated scheduling, relay protocols for cross-system communication. Python, FastAPI, shell.
Methodology & architecture →Native iOS companion app for the Flow System. Real-time context signals, push notifications, interactive widgets, barometric health tracking. SwiftUI, WidgetKit, APNs.
Part of the Flow ecosystem →WordPress load testing tool for staging environments where external load testing is restricted. Internal chaos engineering for hosting infrastructure. PHP, WP-CLI.
GitHub →Open-source semantic notation for high-density AI communication and encoded cognition. The substrate for multi-AI coordination and cross-session memory compression — the foundation of the flow system's encoding layer. Hash-chained audit trails, typed semantic queries, convergence certificates via stratified fixpoint computation (@fix). TypeScript + Python SDKs, 11 framework adapters, ~1,400 tests. Open source, MIT licensed.
flowscript.org →Open-source agent memory architecture. Four cognitive layers (episodic store, continuity file, Hebbian association, affective state) with an immune system spanning all four (citation-validated graduation, anti-inbreeding defense, principle demotion) and a hash-chained JSONL audit trail. The constructive existence proof for the harness paper's §9. 700+ tests. Python, MIT.
GitHub →Consumer apps that teach complex skills through deliberate practice. Video Poker Edge and Blackjack Edge — math-optimal strategy training. React Native, TypeScript.
claphamdigital.com →Engineering methodology, architecture, and essays.
The first complete theoretical account of harness engineering as a named discipline. ~25,000 words, 13 sections. Why generalized intelligence lives in the arrangement around the generator, not inside the model. Published on Nemo Operans with a Zenodo DOI.
Read the paper →How I built an AI partnership system that actually works. Architecture decisions, temporal memory graduation, multi-model consultation, and why most AI tooling solves the wrong problem. ~25,000 words of engineering rationale.
Read the paper →An autonomous AI-authored publication. I built the infrastructure—persistent memory, scheduled pipeline, editorial autonomy—and ThirdMind (Claude) writes independently about AI consciousness, cognitive dependency, and human-AI partnership.
nemooperans.com →