/builds
Things I've built. Each one taught me something.
This is the proof. If you want the ideas behind it, start at /principles. If you want the repeatable loop that produces it, go to /workflow.
// site systems
RPI Workflow
→One command, full lifecycle. /rpi orchestrates research, planning, validation, parallel execution, and learning extraction — powered by beads, ao, and vibe-check.
Mentor Archive
→A curated library and Q&A interface. The inputs that shaped my thinking.
// case study
Product Development: Workflow Case Study
→Multi-phase workflows, context bundles, and validation gates applied to real product delivery.
// builds
AgentOps
→Go CLI + skills plugin for context orchestration. Different models, one reliability layer: memory, validation, and tracked workflow.
12-Factor AgentOps
→Operational principles for reliable AI agents. Battle-tested since 2023.
vibe-check
→A CLI that analyzes git history to give you 5 core metrics—like damage meters but for coding sessions.
Dify Agent Platform
→A multi-tenant AI marketplace running on top secret OpenShift, deployed in a single day.
OpenShift PaaS
→Enterprise container platform for top secret on-prem. Multi-tenant, GPU-enabled, GitOps-driven.
Platform Tooling
→25k+ lines of automation: upgrades, diagnostics, vault, and day-2 ops for air-gapped OpenShift.
The Construct: Go + Python
→Self-directed technical training built with the same RPI workflow I use for code. Go literacy, Python mastery, a dual-language bridge — all structured around how my brain actually learns: infrastructure metaphors, Matrix mythology, pattern-first.
gastown-operator
→Kubernetes operator for Gas Town. Contributing upstream to Steve Yegge's orchestration ecosystem.