Ai

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. ...

A Reusable Access Layer I first built pages, a static-site host with an MCP upload tool. It was useful enough that I kept repeating the design. The cluster now has ten MCP servers: congress-mcp, freshrss-mcp, googlenews-mcp, gsc-mcp, jetlog-mcp, media-mcp, monica-mcp, nodebyte-mcp, pages, and the Kubernetes server. Each server fronts one self-hosted application. The similarity is intentional. They share the manifest layout, bearer-token boundary, hostname convention, and deployment path. Adding the tenth took about forty minutes, most of it spent writing the tool descriptions that decide whether a client can use the server sensibly. ...

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. ...

Introduction Consider an agent running in a cluster or on a server that needs to read the news. The customary response is to provide an HTTP client and permit it to fetch URLs, perhaps through an egress proxy intended to impose a measure of network hygiene. The agent in question is an in-cluster assistant with material access to its environment. It can receive a projected ServiceAccount token, whose effective authority derives from Kubernetes RBAC; it can control home automation; and it can reach several important internal services. Giving a system with that degree of reach a general-purpose fetch(url) tool creates a direct security problem: every page it reads becomes a potential source of adversarial instruction, and every host on the internet becomes a potential destination for whatever information the agent can assemble. ...