A routine homelab hygiene pass turned into a full infrastructure cleanup: Proxmox reboot validation, Uptime Kuma repair, Home Assistant Wake-on-LAN, router reservations, stale device cleanup, and one stubborn BIOS-shaped mystery.
The local router prototype became useful when Hermes turned off a real Z-Wave light through Home Assistant, after USB passthrough, Z-Wave JS setup, entity mapping, and one stale MCP endpoint got fixed.
Turning a local AI policy-layer plan into a static router prototype, with FastAPI, Proxmox LXC, local DNS rewrites, Uptime Kuma monitoring, Spark DeepSeek, and 5090 Granite fallback routing.
A dual Spark DeepSeek endpoint solved the model problem, then exposed the next missing layer: local-first policy routing across household agents, specialist models, paid tools, PAIR, and future homelab nodes.
The dual Spark cluster moves from a working demo to durable household infrastructure: mDNS, reboot recovery, Hermes routing, remote dashboard access, benchmark results, and the first tuning lessons.
A random Tuesday sends an agent over SSH into the homelab to check every piece of software running there. Coder jumps two full versions, cloudflared and RustDesk get patched, and llama.cpp pulls in 317 commits, all with zero manual steps.
A new local model gets validated by a dashboard feature built before it existed. A DNS outage traces back to two unrelated bugs. A deliberate reboot of the homelab’s Proxmox host finds a third bug neither fix would have caught.
A phone-friendly status page for a two-machine homelab, built in phases. Why it lives on the Proxmox box next to Home Assistant instead of the AI workstation, how it talks to Uptime Kuma with no REST API to speak of, and why the third phase, waking the workstation remotely, is still waiting on a cable move.
Episode 4 gives an agent real write access to Uptime Kuma, retires the last manually-copied secret files, test-builds Proxmox Backup Server in Docker (catching a build that silently deleted the very package it installed), and catches a Wake-on-LAN plan that was about to fail for a reason nobody had checked yet.
Four tables disappeared without a trace on the Substack mirror of a recent post — not a bug in this site’s pipeline, but a platform limitation with a fix worth building anyway. Then a full, risk-sorted update pass across every tool the homelab runs on, including an NVIDIA driver near-miss and a Home Assistant instance retired for real this time. Closes with a one-character YAML fix that had taken down the entire site’s production build.
Episode 3 installs HACS and an MCP server entirely over SSH, chases a phantom outage down to a single stuck config value, and wires nine Uptime Kuma checks with Discord alerts, then fixes a cron bug and a false-alarm habit before publishing.
Episode 2 of the SmartThings-to-Proxmox series: hardening the ThinkCentre, wiring up Tailscale so a Coder Agent can SSH in and administer it directly, standing up the Home Assistant OS VM, Uptime Kuma, and AdGuard Home, and ending on a single page load that quietly fired 53 blocked ad-tech requests.
Kicking off a series on replacing a Samsung SmartThings hub with a self-hosted Home Assistant box. Episode 1: picking the hardware, fighting a Lenovo BIOS setting hidden behind a decoy, and the increasingly absurd path to actually getting an OS onto the machine when there wasn’t a single working USB drive anywhere in reach.