Notes on the things I actually run and build, from homelab monitoring to the terminal I'm working on.
OpenClaw ships QMD, an embeddings-and-reranker vector memory, as the default. For a homelab it's overkill. Here's the lighter setup I run instead: a concept index plus a small CPU embedding model, indexing notes and chats on a schedule, no GPU.
Read the post →
I run Claude Code on my home server and reach it over Telegram, so my homelab has a chat window now. The standing jobs, the two watchers I lean on, and what I learned running too many agents at once.
A small Grafana stack for the home server, the one security decision I reversed when I pulled Tailscale off a public VM, and how I keep six months of history from vanishing if a disk dies.
More posts as I build. Check back soon.