Exposing Local LLMs to the Web: LM Studio + Caddy
Learn how to securely expose your local GPU models to the public web using LM Studio's Local Server and Caddy reverse proxy on Windows.
Read full post →
Lab Notes
Blog
Technical breakdowns, build logs, and field notes from the lab. Real projects, real infrastructure, no fluff.
How to Run a Private SearXNG Instance on Windows
A comprehensive guide to setting up and running a private SearXNG meta-search engine on Windows using Docker Desktop and WSL2. Take back control of your search data.
Read full post →How I Self-Host an AI-Powered Website with Caddy, SearXNG, and a Local LLM
A complete walkthrough of running a production website on a home server — with HTTPS, a live AI chatbot powered by a local Qwen model, and a real-time news feed pulled through a private SearXNG instance. No cloud, no monthly bills, full control.
Read full post →