Use a personal agent to manage sleep, notes, code, and quakes

Bangkokbuild set up OpenClaw to handle health tracking, note updates, code work, messaging, and earthquake alerts.

Done with OpenClaw· Intermediate

What they did
Bangkokbuild connected OpenClaw with Garmin, Obsidian, GitHub, a VPS, Telegram, WhatsApp, and X. From there, the agent records sleep, health, and exercise information, sends a nudge when they stay up past bedtime, and pings them on Telegram if they go quiet. It also handles code creation and deployment, refreshes daily notes, follows visitors to MenuCapture, and monitors Tokyo earthquakes.
How it went
This was shared as a brief bullet list, so it does not include timings, counts, or any breakdown of reliability. It also leaves out cost and setup effort, though it does show the agent was given broad access to private data and a server.
Tips
Start with the least sensitive permissions and add more only after each connection works. Keep a clear approval step for deploys, edits outside your notes, and any message the agent might send for you.

Try it yourself with OpenClaw

Connect my [sleep tracker], [notes app], [code host], [server], and [messaging apps]. Each morning, take the prior night’s sleep data, write a note for me, and if I am still awake after [bedtime], send a reminder. Also watch [earthquake feed for my city] on a regular schedule and notify me only when an event crosses [threshold]. Before you deploy code, edit anything outside my notes, delete files, submit forms, or message someone, pause and ask me to approve that action. First verify every connection with a harmless test, then tell me which ones succeeded.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.