Homelab

Introduction Nine namespaces in my cluster depend upon a local language model. The SDR research stack tags transcriptions, the politics dashboard summarizes feeds, the congressional-trade tracker prepares daily summaries, and several agents submit work to the service continuously. Despite their differing purposes and operational rhythms, each consumer was designed to address one stable hostname on port 11434. That hostname fronts two active Ollama deployments: an RTX 5090 in a desktop tower that is intentionally powered down at intervals, and an NVIDIA GB10 Spark board whose unified-memory architecture causes GPU-backed allocations to count against the pod’s memory limit. The repository contains a CPU-only deployment manifest, but the active Kustomization excludes it under ordinary circumstances. The Spark deployment is therefore the operational fallback. ...

Introduction I use Claude Code for substantial one-off analysis, and its output is frequently a single self-contained HTML file. Examples include a flight-log dashboard, an interactive trainer derived from an audiobook transcript (described in Building Interactive Trainers From My Audiobook Library), a pedigree chart, and a client map. Each began either as a Live Artifact or as a file in /tmp that I opened with file://, inspected once, and subsequently lost. ...

Building Interactive Trainers From My Audiobook Library I listen to a considerable number of business and leadership audiobooks, yet retain very little of their content a month later. Listening is passive; useful frameworks blur together with time; and “I read that one” readily becomes “I think I read that one.” I wanted the retention without replaying seven hours merely to recover the one idea I needed. I therefore built a compact production process that converts an audiobook into an interactive trainer, in which each concept and example becomes a card supporting three modes: Browse, Flashcards, and Quiz. Each book receives its own self-hosted site on my internal network; during a single afternoon, I applied the process to seven titles. ...

Politics Dashboard: A Self-Hosted, AI-Summarized News & X Feed Reader I built and open-sourced a self-hosted news dashboard that aggregates political news from RSS or FreshRSS, summarizes individual articles with a configurable large language model (LLM), generates a 24-hour thematic digest, and presents X posts with per-account summaries through a self-hosted Nitter instance. The repository is github.com/RobertDWhite/politics-dashboard; it is MIT-licensed, and multi-architecture images are available at ghcr.io/robertdwhite/politics-{api,ui}. The production image is the same image GitHub Actions builds from main. ...

Weather Dashboard: A Self-Hosted, NWS-Grade Weather Operations Console Bottom line up front. I built and now open-sourced a self-hosted weather operations dashboard built around the US National Weather Service api.weather.gov and a stack of other free public sources (NOAA SPC, AviationWeather Center, NDBC, USGS, RainViewer, IEM). For fun, I also pull in APRS stations from my SDR rig. It renders active alerts with VTEC parsing and polygon overlays, NEXRAD and MRMS radar with time-machine playback, severe-weather products from SPC including ProbSevere v3 and GLM lightning, aviation METAR/TAF/AIRMET/SIGMET, marine buoys and tides, USGS earthquakes, AirNow AQI, and a 7-day NWS forecast. It speaks CAP 1.2 to other systems, fans out severe alerts to Slack/Discord/generic webhooks, and supports VAPID web push for the browser. Repository: github.com/RobertDWhite/weather-dashboard. License: MIT. Multi-arch images at ghcr.io/robertdwhite/weather-dashboard-{api,ui}. The image I run in production is the same image GitHub Actions builds from main. ...