AI Enablement Engineer | Operational Intelligence | DevTools Python · Rust · TypeScript · Linux Systems · Full CI/CD
I apply lean manufacturing systems thinking to AI and software engineering. 17 years in enterprise operations (Toyota, IBM) before I touched a model. The result: systems that ship reliably, not just demo well.
AI workflow orchestration — multi-agent pipelines with cost tracking, checkpointing, and structured feedback loops Document intelligence — investigative-grade ingestion, entity extraction, and co-occurrence analysis Developer tooling — CLI utilities for AI teams: spend tracking, agent auditing, context generation Production AI applications — autonomous content pipelines running at scale across multiple languages
Animus — Multi-Agent Orchestration Framework
Coordinate specialized AI agents across enterprise workflows with budget controls, quality gates, and checkpoint/resume. FastAPI backend · React dashboard · 4 packages (Core/Forge/Quorum/Bootstrap) · 37 tools · Quorum coordination protocol (PyPI) · 14,596+ tests · 97% coverage
BenchGoblins — AI Fantasy Sports Decision Engine
League-centric start/sit, trade analysis, and matchup projections. Grok-primary scored LLM routing with Goblin Verdict. Live on Fly.io + Vercel. Next.js · FastAPI · PostgreSQL · Redis · Stripe · 2,647 tests · 98% coverage
EVE Gatekeeper — EVE Online Route Intelligence
SSO-authenticated route planner with 14-layer interactive map, gate camp warnings, expandable risk breakdowns, and Stripe billing. Live on Fly.io + Vercel. Next.js · FastAPI · SQLite · Stripe · 3,177+ tests · edengk.com
DOSSIER — Document Intelligence Platform
Investigative-grade document analysis: ingest PDFs/emails/scans, extract named entities, surface co-occurrence relationships. SQLite FTS5 · Custom NER (4 entity types) · Auto-classification · 1,084 tests · 97% coverage
agent-lint — Agent Workflow Auditor
CLI tool for cost estimation and anti-pattern detection in agent workflow YAML configs. PyPI Static analysis · 17 lint rules · CI integration · Zero LLM dependency · 296 tests · 98% coverage
Argus Overview — Linux Multi-Window Manager for EVE Online
Real-time 30 FPS window previews, team management, auto-tiling layouts, EVE settings sync. 2,500+ downloads · 2,179 tests · 100% coverage · PyPI
WatchTower / Witness — On-Chain Intelligence & Dossier NFTs
Discord bot with 16 commands, Dossier NFT minting (3 tiers on Sui testnet), Oracle Loop for on-chain entity profiling, reputation cache, Stripe + SUI payments. FastAPI · Sui Move · Discord.py · dApp Kit · 774 tests
Monolith — EVE Frontier Anomaly Detection
35 detection rules, 17 checkers, item ledger, chain state verification via Sui GraphQL, public API v1, webhook subscriptions, Canvas2D heatmap with 24K systems. FastAPI · SQLite · Sui GraphQL · 312 tests · anchormd 100/100
Frontier Tribe OS — Corp Management Dashboard
7 modules: Kill Feed, LLM Briefing, System Intelligence, Alert Config, Pilot/Corp Intel, Battle Reports, Signature Resolution. Live on Fly.io + Vercel.
| Tool | What | Tests |
|---|---|---|
| anchormd | AI agent context file generator/auditor + tech debt scanner (PyPI, anchormd.dev) | 693 |
| promptctl | Claude API toolkit — prompt engineering, code review, doc intelligence (PyPI) | 330 |
| context-hygiene | Context window optimization — detect bloat, measure signal density (PyPI) | 398 |
| memboot | Zero-infra persistent memory for LLMs — SQLite + TF-IDF (PyPI) | 304 |
| ai-spend | AI API cost aggregator — Anthropic + OpenAI billing in one view (PyPI) | 267 |
| mcp-manager | MCP server manager — discover, monitor, manage across IDEs (PyPI) | 158 |
83 workflow files across 20+ repos. 0 open code scanning alerts. 0 dependabot alerts.
| Capability | Evidence |
|---|---|
| Containerization | Multi-stage Dockerfiles, docker-compose, templates |
| Kubernetes | Deployments, HPA, Ingress, Kustomize, Helm chart |
| CI Pipelines | Lint → test → SAST → build → deploy across Python, Rust, TypeScript |
| Security Scanning | CodeQL + gitleaks + Bandit + Semgrep + Trivy + pip-audit |
| Live Deployments | 9 services on Fly.io + Vercel (see Proof below) |
| PyPI Packages | 11 packages via OIDC trusted publishing |
| Benchmarks | Automated performance regression tracking on gh-pages (3 repos) |
| Metric | |
|---|---|
| Tests across active repos | 40,000+ |
| Projects with CI green | 20+ |
| Live deployments | BenchGoblins, EVE Gatekeeper, WatchTower, Monolith, Frontier Tribe OS, anchormd + license server, AI Cards, StayCards |
| PyPI packages | anchormd, agent-lint, ai-spend, promptctl, context-hygiene, mcp-manager, memboot, argus-overview, convergentAI, G13-linux, LikX |
| Security posture | 0 code scanning alerts, 0 dependabot alerts across all repos |
| Real users | Argus Overview: 2,500+ downloads |
| Domain | Tools |
|---|---|
| Languages | Python, Rust, TypeScript |
| AI/ML | Claude API, OpenAI, Grok, Ollama, multi-agent orchestration |
| Backend | FastAPI, SQLite, PostgreSQL, Redis |
| Frontend | React, Next.js, React Native/Expo, PySide6 |
| Blockchain | Sui Move, GraphQL, dApp Kit |
| Infrastructure | Docker, Kubernetes, Helm, GitHub Actions, Fly.io, Vercel |
| Security | CodeQL, Bandit, Semgrep, Trivy, gitleaks, SAST pipelines |
Operational reliability over algorithmic elegance. A system that ships predictably beats a system that demos brilliantly. Standard work, visual management, poka-yoke — applied to software.