Track food and symptoms in a health log via Telegram
An OpenClaw agent logs meals and symptoms from Telegram messages into a markdown file, sends reminders, and runs a weekly pattern analysis; this is a tutorial-style setup.
Done withOpenClaw
- What they did
- You message a Telegram topic with what you ate or how you feel. The agent appends a timestamped entry to a markdown health log in its memory folder. Cron reminders go out at 8 AM, 1 PM and 7 PM. Every Sunday it analyzes the week's log and posts the patterns it finds back to the same topic. It needs no skills, only a prompt and a cron job.
- How it went
- The article gives no measured results. It describes the kind of pattern the analysis should catch, such as dairy followed by headaches three Wednesdays running. It calls this the lowest-effort project on its list.
- Worth knowing
- The article says setup takes under an hour if OpenClaw is already running. It also advises binding OpenClaw to 127.0.0.1 first, because the default exposes it on every network interface.
Try it yourself with OpenClaw
Set up a health log I can use through Telegram. When I message what I ate or any symptoms, add a timestamped entry to a markdown file, remind me at [times] to log, and every [Sunday] send me a summary of patterns between foods and symptoms. Finish by logging a test entry and showing me the file. Treat the summary as observations only, not medical advice.
Source: datacamp.com · Undated
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Manage 18 agents from a Notion workspace
Notion used as the control plane for a fleet of 18 OpenClaw agents.
Automate freelance admin with a morning briefing agent
An OpenClaw agent sends a Telegram morning briefing, drafts weekly client status emails sent after one-tap approval, and chases follow-ups, cutting admin from about 9 hours to 20 minutes.
Triage failed GitHub Actions runs and self-heal flaky tests
A QA engineer's OpenClaw agent reads failed CI logs, classifies failures, posts analysis to GitHub and Slack and opens issues; flakiness fell from 8% to 0.8%, though it once wrongly altered an assertion.
Get a second opinion on an MRI
One person's account of using Claude Code to analyze their own MRI.
Unsubscribe from unread mailing lists via Gmail
Reporters connected Muse to Gmail; it found never-opened emails, let the user choose which to drop, then carried out the unsubscribe requests.
Assemble an immigration document package
A user had ChatGPT browser use gather seven years of taxes, bank statements and immigration documents into a package in minutes.