Building systems to test the ideas.

Project · 2026

MemoryOS

Local-first memory pipeline for macOS — captures screen, audio, email, calendar, and documents as structured Markdown for AI-powered querying. Reference implementation for Context Compilation Theory.

Reference Implementation for Context Compilation Theory

• Source code ↗

Project · 2026

Praxo-AgentOS

Governed lifecycle tooling for agentic engineering work. Reference implementation for Cybernetic Software Delivery — nine-stage lifecycle, artifact taxonomy, four-tier governance, and DORA-extended metrics.

Reference Implementation for Cybernetic Software Delivery

• Source code ↗

Project · 2026

Praxo-PICOS

Local-first personal intelligence operating system for macOS. Captures context from email, calendar, screen, documents, and notes — makes it searchable and actionable. Privacy-preserving, self-healing, commercial-grade.

Personal Intelligence Operating System

• Source code ↗

Project · 2026

SemanticStudio

An open-source, data-first multi-agent chat platform with 28 configurable domain agents, 4 fully-customizable chat modes, 4-tier memory with Context Graph, GraphRAG-lite, self-learning ETL, and comprehensive observability.

Open-Source Multi-Agent Chat Platform

• Source code ↗

Project · 2025

3D Ontological Data Architectures

Constructing three-dimensional ontological representations that capture the full complexity of enterprise data architectures—enabling AI systems like RAG and recommendation engines to navigate semantic relationships with unprecedented depth.

Spatial Knowledge Graphs for AI Systems

Project · 2025

Agentic RAG Architectures

Designing and implementing production-grade agentic RAG systems with 12-15+ specialized agents that optimize retrieval pipelines across terabytes of enterprise data, overcoming recency bias and attention dilution through advanced context engineering.

Multi-Agent Retrieval Systems at Terabyte Scale

Project · 2025

Attention-Optimized Context Engineering

Advanced context engineering techniques that exploit transformer attention patterns to maximize information utilization in agentic systems—positioning critical context where attention naturally focuses.

Hacking Transformer Attention for Agentic Systems

Project · 2025

Advanced Context Engineering

Research and implementation of novel context engineering techniques that overcome fundamental limitations in attention mechanisms, enabling more effective use of extended context windows in production LLM applications.

Memory Optimization for Large-Scale RAG

Project · 2025

Future of AI Operating Systems

Research and published writing on the evolution of software interfaces toward AI-native paradigms, where traditional SaaS becomes headless infrastructure and agentic systems become the primary user interface.

Headless SaaS & Agentic Interfaces

Project · 2025

Real-Time Quality Feedback Systems

Developing production systems for real-time AI output quality assessment, including hallucination detection, factual grounding verification, and reinforcement learning-based response optimization.

Hallucination Detection & Continuous Learning

Project · 2025

Reinforcement Learning ETL Pipelines

Building next-generation ETL pipelines powered by reinforcement learning with advanced Plan-Act-Reason loops that enable true self-learning capabilities—pipelines that reason about their transformations and continuously optimize their behavior.

Self-Learning Data Systems with Advanced PAR Loops

Project · 2025

Self-Learning Data Pipelines

Building intelligent data integration systems that use Plan-Act-Learn loops to continuously adapt, learn, and optimize—moving toward fully autonomous data pipeline management.

Autonomous ETL with Plan-Act-Learn Loops

Project

Enterprise Data Fabric

Designing and implementing enterprise data fabric architectures that unify disparate data estates, enabling trustworthy AI through comprehensive governance, lineage, and quality frameworks.

Unified Data Architecture for AI-Ready Organizations

Project

Academic Teaching & Research

Over two decades of graduate-level teaching, doctoral mentorship, and academic research in AI, data architecture, and enterprise systems. Published author of books, academic papers, and industry courses.

Shaping the Next Generation of AI Architects

• Source code ↗

Tool

AI 101

Interactive foundations for understanding AI systems.

Interactive learning surface

Tool

AI Systems Lab

System Designer, Value Reactor, and Governed RAG Foundry.

Three full-screen system tools

Tool

Digital Twin

Interactive conversation grounded in the public corpus.

Conversation interface

Environment

HomeLab

Local AI infrastructure, deterministic routing, and an auditable control plane.

Four-machine local AI environment

Reference

Learning

Courses, teaching, and interactive foundations for AI systems.

Teaching and interactive learning surface

Project

SemanticStudio

Open-source multi-agent chat platform with memory, GraphRAG, and ETL.

Multi-agent platform reference build

Reference

Stack

Tools, frameworks, and hardware used to build local AI systems.

Operating stack and research focus areas