Ollama

Introduction Hermes is the agent I use when a conversation has to reach the infrastructure. I address @hermes:white.fm in an end-to-end encrypted Matrix room. Hermes reasons through the local model route in my cluster, then invokes a finite set of tools against services with their own operational boundaries. Three previous pieces describe the components in isolation: the local Ollama router, the encrypted Matrix notification hub, and the MCP server fleet. Hermes is where those systems meet. Matrix provides the private conversation, Ollama provides the default inference path, and Model Context Protocol (MCP) servers supply the functions through which an answer may become an action. ...

Introduction An RSS reader is very good at collecting material and almost useless at telling me what deserves the next ten minutes of my day. On a busy morning, a hundred stories can arrive, four may alter a customer conversation or an account plan, and the rest bury them under wire copy, recycled commentary, and headlines whose relationship to the underlying event is thin. Keyword alerts do not repair that problem. They report a word’s presence, then happily ring for a passing reference, a syndicated rewrite, an executive departure, a funding round, and a lawsuit with no discernment among them. The human cost is familiar. An alert stream that repeats itself becomes background noise, and the article that did matter gets read after the meeting for which it would have been useful. ...

Introduction Nine namespaces in my cluster send work to a local language model. The SDR research stack tags transcriptions, the politics dashboard summarises feeds, the congressional-trade tracker prepares daily summaries, and several agents submit work throughout the day. They all call one stable hostname on port 11434. Behind it are two very different Ollama deployments. The primary is an RTX 5090 in a desktop tower that I deliberately power down at intervals. The fallback is an NVIDIA GB10 Spark board, where CPU and GPU share memory and GPU allocations count against the pod’s memory limit. The repository also contains a CPU-only manifest, although the active Kustomization excludes it. The Spark is the backend that remains when the tower is dark. ...

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. ...

This post was originally published at w3rdw.radio, the ham radio blog of Robert White (W3RDW). It is cross-posted here for the WhiteMatter Tech audience. Always-On SDR: Building a Multi-Band Radio Intelligence Platform on Kubernetes I have been quietly building something i am pretty excited about. The idea started simple enough: i wanted a permanent, always-on radio monitor for 2m. It grew into something considerably larger. Today the stack covers 2m, 70cm, and the full HF spectrum from 3–28 MHz simultaneously: recording, decoding, transcribing, and tagging everything it hears, around the clock, with no manual intervention. ...