Writing

Local Agents Are Not Toys

Local LLMs on the M5 Max have become useful for bounded agent work, but they are not Amp or Claude killers yet.

Throwing Hermes into the Swamp

Hermes and Swamp finally worked once I stopped chasing install ownership and fixed the session snapshot that every tool subprocess sources.

Agents Make Homelab Alerts Boring

A Frigate storage alert became a small example of why agents and Swamp are working so well in my homelab: bounded context, reviewable changes, and asynchronous fixes that preserve headspace.

View all writing →