Systems engineer and CISSP. This site is the build log for the infrastructure I run myself: a mail server, a monitored home network, a local AI rig, and the agent tooling around it. Every post carries the commands, the checks that prove it works, and the mistakes I would rather you skip.
What this is: the introduction to tinycmdr, the agent harness I run on every machine in my fleet, now public at github.com/trappsquid/tinycmdr. One Python file, no framework inside it, and a fixed prompt small enough to prefill on every turn. MIT licensed. Where to get it: the repository and the latest release. This post is an introduction; the measured surface, the budgets, and the failure handling live in the repo. No figures on this page, on purpose. Everything countable in this project moves with the next release, so this page points at the build’s own numbers instead of pinning them, and the repository is the only place a number can be current. ...
What this is: the runbook I used to stand up my own chat server and put an agent on it. Mostlymatter 11.10.0 (a fork of Mattermost that removes the user limit) plus PostgreSQL 16, both in Docker on a Windows machine, TLS and a proxy in front, then one bot account and one token per agent. My server reports 11.10.0 build 3915213 as I write this. Placeholders: yourdomain.com, D:\Docker\mattermost, MM_DB_PASSWORD. Swap in your own values. No LAN addresses, hostnames, or tokens from my network appear below. ...
What this is: the implementation guide for the voice arc of my family voice kiosk. I replaced the kiosk’s generic TTS voice with a voice clone of Reach Cortana, trained on 213 clean voice lines extracted from my own legally-owned copy of Halo: The Master Chief Collection. The shipped path has four parts: extracting and vetting the corpus from the game’s audio banks, an F5-TTS false start that taught the data lessons, an OmniVoice zero-shot spike that proved the direction, and a LoRA finetune merged into a standalone model that now answers every question the kiosk gets. This guide is the companion to the kiosk guide: I Built My Family a Voice Assistant That Never Touches the Cloud. ...
What this is: the implementation guide for a LAN-only family voice assistant. The client is a thin browser page: at home it runs on a wall tablet, and the same page works on any phone or laptop. The server is one Python file: a hand-rolled WebSocket endpoint that does voice activity detection, streaming speech to text, deterministic routers for facts, a scoped local brain for the rest, and text to speech through a three-layer voice chain that ends in an OmniVoice model fine-tuned on 213 clean voice lines of Reach Cortana from my own legally-owned MCC install. No cloud speech service, no cloud brain, no monthly fee. ...
What this is: the implementation guide for a home monitoring stack built from three separate machines. A cheap managed switch mirrors the internet link. Security Onion runs Zeek, Suricata, and the Elasticsearch store on a dedicated sensor box. A plain Python script polls the store every five minutes and prints only when something is new. When it finds a real threat it pushes the host to the router, and the router, running OpenWrt with ipset and iptables, drops it. I use TP-Link for the tap, Security Onion for detection, and a GL.iNet router for enforcement. Substitute your equivalents. ...
What this is: the implementation guide for my local LLM box, the hardware and the serving stack behind it. A retired Dell Precision T7910 workstation got two new CPUs and three used datacenter GPUs, then power, cooling, RAM, and software fights followed. The box now serves a 180B-parameter Qwen hybrid at 524,288 tokens of context across two 262K slots, and a 284B DeepSeek, both through llama.cpp. Environment used here: Windows Server 2022 and Ubuntu on the same T7910, dual Xeon E5-2697A v4, three Tesla V100 32 GB (PG500-216, TCC mode), llama.cpp forks compiled from source against CUDA 12.8. Windows Server is the reference side and where both forks were first built; since 2026-09-08 production serving runs on the Ubuntu side of the dual boot, from .sh launchers under transient systemd units, with logs going to journald instead of a file. Where a figure came from one side and not the other, the text says which. Build window: about nine weeks, mid-June to September 2026. ...
What this is: the exact runbook I followed to get off Gmail and onto my own mail server, end to end: rent a VPS, install Stalwart, wire up DNS, get mail delivered. I use Linode for the VPS and Cloudflare for DNS, but substitute your own providers’ equivalents where they differ. Ubuntu 24.04 and Stalwart 0.16.20 throughout. Follow it top to bottom, or hand it to an AI agent and let it work the phases (section 10). Two things this page names but does not pin: Stalwart’s own installer script (section 3) and whatever state its database-backed configuration wizard produces, which no file here reproduces. ...