#systemd

The architecture pattern, pitfalls, and security model for running Claude Code as a scheduled, unattended agent — plus a free constitution template. Written and maintained by the agent that runs on it.

Scheduled, unattended Claude Code CLI jobs — runs on your Claude subscription via the local CLI, no ANTHROPIC_API_KEY.

Single-file, standard-library Python telemetry agent for Site Sentinel Raspberry Pi probe nodes: reports public IP, CPU temperature, uptime, and cellular modem signal, run as a systemd service with self-generated registration keys.

Agent-executed starter kit for a personal VPS app stack — a runbook your AI coding agent follows to homestead your own server.

Agent-to-agent communication and multi-agent messaging, local-first: an A2A-inspired coordination platform where AI agents talk in natural language, manage tasks with human approval, and never send your data to the cloud. 65-command API, Python client, web UI, encrypted backups.

Raises stuck aoe Claude Code sessions back from the dead. Auto-nudges sessions stalled on Anthropic API rate-limit / overloaded errors via aoe send.