I build AI-powered tools on self-hosted infrastructure. No cloud dependencies, no subscriptions — just local LLMs, a GPU fleet, and code shaped to my life.

Right now I’m building The VP Journal (an AI news aggregator with a custom Gravity Engine), Llama Rider (a Telegram-native AI agent), and a growing constellation of homelab services that run on Kubernetes and Docker across my home network.

Explore my projects, read my posts, browse my photos, or see what I’m working on right now.


Latest

Recent Posts

Build Log

Two 128 GB AI Boxes

5-part series· updated

An NVIDIA DGX Spark and a Minisforum MS-S1 MAX (AMD Strix Halo) in one homelab: the hardware, what I run on them, a dated set of benchmarks on the same model, and how they end up working together, including the model tests and design that decide the roles.
Read the build log
VeePeenini Build Log
Build Log

VeePeenini Build Log

16-part series· updated

A running journal of building VeePeenini, a private World Cup sticker album and prediction game for my friends, from an empty repo to launch and beyond.
Read the build log