This series is about the shift from choosing a model to running an AI setup as infrastructure.

The model still matters. But the useful system around it is bigger: agent workflows, local context, memory, tool access, observability, secrets, and boundaries.

Posts in the series

  1. From Chatbot to Self-Hosted AI Infrastructure
    The overview: why the setup became a stack instead of a chat window.

  2. The agent layer: the model was never the system
    How Hermes, model routing, tool use, scheduled work, Telegram, and Claude review fit together.

  3. The context layer: context is a system, not a scrapbook
    How Obsidian, local retrieval, Qdrant, and memory make the assistant work from sources.

  4. The boundary layer: tools need limits
    Why secrets, Home Assistant, voice, MCP permissions, and monitoring need safe defaults.

Main components

I am keeping the overview posts readable. Deeper configs and diagrams belong in separate reference posts.