Build Medic: An Agent that Helps Builds Run Green
My team was nervous about an AI agent in our Kubernetes clusters - so I built a prototype with cost and safety guardrails in code, using the Claude Agent SDK.
Exploring Nscale’s Fleet Operations - in a Home Lab
I rebuilt the node lifecycle from Nscale’s Fleet Operations in a home lab - MAAS, Temporal, Slurm and OpenStack provisioning Intel NUCs from rack to workload to reclaim.
Mac Studio: The Best Local LLM Workstation Money Can(‘t) Buy
Why an M4 Max Mac Studio with 128GB of unified memory is the best local LLM workstation for developers - running Qwen3, Ling and Gemma with llama.cpp and MLX.
All Agents Report Back to Me: Monitoring AI Agents with Chat
Run a self-hosted Rocket Chat server so your AI coding agents post progress to one chat — watch long-running sessions from your phone and reply to steer them.
Why Would You Write a Book About Docker in 2025?
Docker is established tech now - so why would anyone buy a book about it? Because most people only learn a fraction of what Docker can do from their day job, and it pays to learn it all.
