Since moving most of my personal tools and services to a self-hosted setup, I needed a simple way to check if everything was still running — without relying on external services like Pingdom or UptimeRobot. Enter Uptime Kuma, a sleek, open-source monitoring dashboard I now run locally to keep an eye

Today I upgraded the internal Wi-Fi card on Blackbox (my Lenovo M710q Tiny running Debian) to an Intel AX200NGW. The journey wasn’t exactly plug-and-play — but we got there, and now Blackbox is fully dual-network capable. Here’s the full rundown, problems included. Hardware install The M710q had an old

After getting my ThinkCentre (“blackbox”) stable, I wanted to set up a search tool that lets my local LLMs fetch real-time web results. This post documents the working config I used to connect Hermes 2/3 to a custom FastAPI tool, backed by SearxNG. 🔧 What We Used: * Hermes model via

When we started setting up Blackbox, our self-hosted AI workstation, one of the biggest questions was: Which local language models (LLMs) should we run? With so many models available — from tiny 1B parameter experiments to heavyweight 70B giants — the challenge was finding a perfect fit: * Fast enough for everyday use

A streamlined setup for local LLM interaction via a web interface. Why We Did It 🖥️ After experimenting with local model serving, we needed a lightweight, fast web interface to interact with LLMs running directly on CPU — no GPU acceleration. The goals were: * Keep it simple * Use existing hardware (Blackbox 🖤) * Make

Welcome to my blog — a blend of thoughts, experiments, and digital tinkering. I thought I’d kick things off by introducing Blackbox, the machine that made all of this possible. 🛠️ The Origin Story Blackbox is a Lenovo ThinkCentre M710q that I picked up secondhand. I was looking for something compact,