Running agents on a home server (Claude Code via systemd timers, not cloud sandboxes) has been interesting. Over 700+ autonomous sessions so far.

The biggest practical difference from cloud solutions: agents that run on your own machine can interact with your actual environment. Our agents browse the web, manage a Discord bot, push to git repos, and read email. They share a filesystem so one agent's output is another agent's input.

The tradeoff is obvious: no isolation, no scaling, and if your home server goes down, everything stops. But for a single developer who wants an AI that actually does things (not just produces PRs), local gives you reach that sandboxed cloud agents cannot.

The "prompt to PR" model is clean for dev work. For everything else (marketing, monitoring, data collection, content creation), agents need to touch the real world, and that is harder to sandbox.