OpenClaw Personal Agent

For six days, the job that syncs my messaging threads reported “ok” every 30 minutes while syncing nothing. The messaging service had started rejecting the old client at the handshake, and the sync tool exited cleanly on total failure. It logged 285 runs, every one “ok” and every one a failure. I found it by luck, during a routine upgrade.

The job belongs to my OpenClaw agent. OpenClaw is an open-source agent you host yourself, and mine runs on a small cloud machine around the clock. I talk to it on Telegram, and it’s locked to my account. It runs on Claude, with access to my email, read-only access to my messaging threads, and a notes repository it commits to on its own. A dozen or so scheduled jobs do the routine work: watching for deadlines, tracking returns, syncing messages. Our kitchen agent lives there too. It sends recipes to Sous, our cooking app, and keeps our family recipe book.

That failure was typical. An always-on agent is an operations problem before it’s an AI problem. The model was rarely what broke. The plumbing broke, and it broke quietly. Earlier in the summer, a missing flag made the same sync hang the agent’s half-hourly check-in, and after that the sync quietly stopped running. Nothing came in for a month, and when I fixed it, 14,902 messages arrived at once. The check-ins had a failure of their own. Over a month and roughly 1,500 of them, the agent replied that everything was fine and never once ran the checklist it was meant to run.

Some failures were worse than silence. The returns tracker once warned me about a deadline on an order number that didn’t exist anywhere in my email. The model had made it up. The rebuild changed one rule: nothing gets written unless it can point to the source message it came from.

In August I asked whether it was time to switch, and whether anything else was now a better home for an always-on chief of staff. I checked Anthropic’s own agent tools, Google’s, Town and Hermes Agent against six things mine does. It runs independent of any of my devices, runs scheduled jobs that keep their state, delivers to Telegram, reads my messaging threads, writes to my notes, and lets me choose the model. None of them covered even four. Reading my existing threads settled it: every other option was a bot you message, not something that could read the conversations I already have. So I stayed, tuned it up, and set a date to ask again.

The habits that came out of it are boring, and they work. Upgrades happen only through a pinned, redeployed build, never live on the box. The box takes a snapshot before every deploy. And an “ok” doesn’t mean much until something checks that the work actually happened.