Posts

From Chatbot to Self-Hosted AI Infrastructure My AI setup started as a model choice: GPT or Claude, local or hosted, bigger context window, cheaper tokens. That still matters, but it is not enough once an assistant can read notes, call tools, remember preferences, and interact with infrastructure. This post covers the shape of the setup. The deeper details belong in the follow-up posts. The setup in layers At home I run Hermes as the agent layer on my main Linux machine. It talks to model providers, but it also has access to local tools, memory, scheduled jobs, and messaging. Around that sits a Docker-based infrastructure stack for knowledge retrieval, memory, search, monitoring, secrets, reverse proxying, and voice experiments with Whisper, Piper, XTTS, and Ollama. ...

After more than seven years at Equinix, I’m making a change. On February 1st, I’ll be starting as Team Lead and Product Owner at Topicus. The Equinix chapter When I joined Equinix back in 2019, I had no idea what the journey would look like. I started as a Deployment Engineer—hands-on, technical, focused on getting things done. Over time, that role evolved into something completely different: Product Owner. The company transformed around me too. What was once a local team became part of a truly international organization. I learned what it means to collaborate across borders, time zones, and cultures. Working with colleagues from APAC, EMEA, and the Americas taught me more about communication and alignment than any training ever could. ...

My Self-Hosted Docker Infrastructure Why Self-Host? Before diving into the technical details, let me explain why I chose this path. Self-hosting gives me: Control over my data - No third-party has access to my files, passwords, or personal information Privacy - Everything runs on my own hardware, behind my own firewall Learning opportunities - Running production services teaches you things you can’t learn from tutorials Cost savings - One-time hardware investment vs. ongoing subscription fees Customization - I can tweak and optimize everything to work exactly how I want But self-hosting isn’t just about avoiding Big Tech. It’s about building something you understand from the ground up. ...

Docker Swarm using DietPi Why DietPi? DietPi strikes the perfect balance: it’s lightweight, actively maintained, runs on tons of devices, and is incredibly easy to configure. Whether you’re using Raspberry Pi, other single-board computers, or even virtual machines on Proxmox or VMWare, DietPi makes cluster deployment straightforward. Note: This guide assumes you’re using Raspberry Pi or similar SBCs. If you’re running on Proxmox or VMWare, some steps—especially editing dietpi.txt—will differ slightly. ...