-
When tools became the interface: from a chat bot to 455 MCP tools
In March 2026 my lab ran on scripts and a chat bot. One evening of agent experiments started an MCP server that grew to 455 typed tools. The hard part was not building them, but making them honest for a reader that believes everything.
-
Why I threw away my first security lab after one month
My first home security lab grew to 50+ tools in a month and became too tangled to trust. On 23 May 2026 I rebuilt it from scratch in a day, and refused to switch the old one off until both counted the same attacks.
-
My website stopped describing the lab and started showing it
In April 2026 every number on my site was typed by hand and stale within hours. On 14 October a redesign went live that is built around live evidence from the lab: library size, sealed reports, running pods. Why a portfolio should show, not describe.
-
After the wipe: six habits that changed how I run my home lab
A test deleted my home folder in ten seconds. Recovery took two days; the habits it left took longer. Freeze before you fix, reboot on purpose, back up the boring files hourly, commit everything, and give agents their own user.
-
One machine, everything: what I would do differently, and what's next
One workstation runs my whole lab: Kubernetes, a 120,000-work library, honeypots, local AI. Seven months of records hold 253 mistakes. What one machine gave me, what it cost, what I would do from day one, and what comes next.
-
From watching to answering: when my home lab began to defend itself
In April 2026 my lab blocked a hostile probe by itself in under 60 seconds. Then I learned how little of that protection was mine, and how automated defence can fail silently or hurt its own network.
-
A post-reboot check script for a one-machine home lab
A cold boot of my lab produced 37 failed jobs; three were real defects hidden for up to two weeks. Here is the read-only OK/FAIL script I now run after every reboot, and the failures it catches.
-
Swapping an 8 GB NVIDIA card for a 32 GB AMD GPU: what broke
I replaced an RTX 4060 Ti with a 32 GB Radeon AI PRO R9700 for local AI. Ten things broke, mostly silently; here they are with fixes, and the before-and-after throughput.
-
A passive GPU in a tower: VRAM hit 106 °C while the core throttled
My new 32 GB passive GPU had no plateau under LLM load and its memory reached 106 °C. Measurements, the limits that were silently ignored, and the fan, power cap and clock limit that fixed it.
-
Read, write, critical: permission tiers for a local AI agent
Every tool call my local AI agent makes is rated read, write or critical. Writes need my approval, critical actions need a one-time code bound to that exact operation, and unattended runs only propose.
-
Self-hosting email with Stalwart: deliverability and data-store traps
In October 2026 Gmail started rejecting mail from my own domain, and my DKIM key in DNS had lost every letter n. Seven traps from running Stalwart at home, and the mechanism behind each.
-
Why my long CrowdSec bans vanished after two days
CrowdSec's alert flush deleted my year-long bans after ~48 hours, a systemd timer sat dead for 24 days, and the fix triggered 18 router re-add storms. Mechanisms and fixes.