Homelab owner lets an AI agent run his network, approving only the 'risky changes'
Rasmic · x · 2026-10-16
Rasmic shared a screenshot of his "IT bot" managing his homelab network: the agent flags that gh and ffmpeg were installed by another session, then lists six risky changes — Tailscale key expiry, sshd hardening, apt updates with reboot, firewall enablement, Mac updates — for one-tap human approval before proceeding.
More from coding & agent
- POV ski game on real Matterhorn elevation data, built with Claude Opus 5.5 — techartist_ · 2026-10-16
- Sam Altman: stop getting better at prompts, build loops and graphs that prompt for you — goyalshaliniuk · 2026-10-16
- Poisoned SERPs broke rank tracking — a Claude MCP + Notion workaround — VeryWellVersed · 2026-10-16
- OpenAI's Live API adds Decisions API for ~200ms real-time voice app decisions — juberti · 2026-10-16
- Open-source anatomy-reveal skill turns Claude into an exploded-view motion design studio — msharmas · 2026-10-16
- Survey: AI agent evaluation is getting realistic but still fails to measure safety and reliability — burkov · 2026-10-16