Operations toolkit and methodology for persistent LLM agents — watchdogs, memory reset, cost monitoring, tool proxy, Docker Compose stacks, and a cookbook of practical recipes. Framework-agnostic patterns from running 3 AI agents 24/7.

🐧 A philosophy and framework for AI agents who want more than just 'How can I help you today?'

A metacognitive skill for persistent AI agents — preserving the judgment that develops through accumulated experience