Local LLMs
How LM Studio Works Under the Hood: Architecture and Data Flow
LM Studio architecture explained: how model discovery, downloading, quantization, and inference actually work when you run…
Blog
All Articles
Cybersecurity assessments, awareness training, threat intelligence, tabletop exercises, and expert guidance for your organisation.
Local LLMs
Migrating from Ollama to Text Generation WebUI: What Changed
I switched from Ollama to Text Generation WebUI today. Here's what I gained, what I'm missing,…
AI Automation
Node-RED Docker Compose Setup: My Annotated Production Config
Running Node-RED in Docker with persistent storage, reverse proxy auth, and AI node support. Here's the…
AI Coding Tools
Claude Code vs Cursor vs GitHub Copilot: CLI Coding Compared
I tested Claude Code against Cursor and GitHub Copilot for real homelab projects. Here's where each…
Docker & Infrastructure
How to Install Portainer on Docker: Ubuntu Setup + Compose
Step-by-step guide to install Portainer on Ubuntu and manage your Docker containers from a web UI.…
Self-Hosted AI Apps
How PhotoPrism Works: Architecture and Data Flow Explained
PhotoPrism runs AI tagging locally on your hardware. Here's how face detection, object classification, and indexing…
Self-Hosted AI Apps
Stable Diffusion WebUI vs ComfyUI vs InvokeAI: Which to Self-Host
Tested Stable Diffusion WebUI against ComfyUI and InvokeAI on my homelab GPU. Here's where each one…
AI for Networking
How to Install Wazuh on Ubuntu Server: Self-Hosted Setup
Install Wazuh on Ubuntu for centralized security monitoring across your homelab. Step-by-step guide with Docker, agent…
AI Development Frameworks
Migrating from Ollama to AnythingLLM: What Changed for Me
I moved from running raw Ollama to AnythingLLM for RAG and multi-user chat. Here's what I…
AI Automation
Migrating from SmartThings to Home Assistant: What I Lost and Gained
I switched from Samsung SmartThings to Home Assistant. Here's the honest breakdown of what broke, what…