Collects as they arrive, acts daily

Keep a monthly record of temperatures

Each day's weather is stored, and once a month you get averages and extremes.

Runs: Collects as they arrive, acts daily
Apps: OpenWeatherMap
AI: Not needed
Access: API key

Send this to your assistant

Create a ClickRuntime automation: record the temperature and conditions in Austin every day, and on the 1st of each month email me last month's average, highest and lowest temperatures.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A hobby gardener wants to know whether this autumn is warmer than last, an allotment society wants to settle an argument about the first frost date, and a homeowner wonders why the heating bill climbed. Weather apps show today and tomorrow but forget everything else, and historical data services are overkill, expensive or not specific to your town. Without a record you rely on memory, which is biased toward the unusual days.

Each day, the temperature (and other readings you choose) for your location is fetched and stored. At the end of the month, the stored values are used to compute the average, hottest and coldest days, number of frost days and days of rain, and a monthly summary is emailed to you.

It is a simple way for gardeners, farmers, energy-conscious households and weather hobbyists to build their own record.

What you get out of it

Arguments are settled with data
When someone claims this was the coldest October in years, you can look at the logged values for each day and see whether it was true. Hard numbers also help to correct misleading impressions that come from a few memorable days.
Frost dates come from real readings
Knowing the last spring frost and first autumn frost in your own garden improves planting dates much more than regional averages do. Planting earlier or later by a week based on your own record can mean a better harvest.
Energy costs are easier to explain
Comparing monthly average temperatures with your heating or cooling bills shows whether a high bill came from the weather or from changes in your usage. That is a useful way to understand what drives the bills, and what to expect next winter.
Your own long-term record grows
Months turn into a year of consistent readings for your exact location. After a few years, the record shows patterns that national averages smooth away. Gardeners and growers often value this because their land has its own microclimate.
Monthly summary saves analysis work
Counting frost days or averaging temperatures by hand from a list of 30 numbers is tedious, so the email gives you the results at the end of each month. It saves the evening you would otherwise spend with a calculator and a spreadsheet.

How it works

What happens, step by step

Every day, ClickRuntime records the current temperature and conditions for your city.
The readings build up into a log for the month.
On the 1st of the next month you get an email with the average, highest and lowest temperatures.
The log then starts again for the new month.

Before it runs live

Connect OpenWeatherMap
Paste your automation's link into the other app's webhook settings

What you get

RunsCollects as they arrive, acts daily

Keep a monthly record of temperaturestoday, 9:00Succeeded

Email · Austin weather for 2026-09Average 29.4°C, highest 37°C, lowest 19°C over 30 days.

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Act only on the items that match your own rules, and skip the rest
Add an AI step, for example to summarize, sort or draft a reply
Add another app, for example also send it to Slack
Combine it with other OpenWeatherMap steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

weather_log_for_trends.pyexample

from datetime import datetime, timezone
from clickruntime import on_trigger, credentials, http, state, notify

@on_trigger
def run(event):  # daily
    w = http.get("https://api.openweathermap.org/data/2.5/weather",
                 params={"q": "Austin,US", "units": "metric", "appid": credentials.secret("OPENWEATHER_API_KEY")}).json()
    today = datetime.now(timezone.utc)
    log = state.get("log") or []
    if today.day == 1 and log:
        temps = [t for _, t, _ in log]
        notify.email_me(f"Austin weather for {log[0][0][:7]}",
                        f"Average {sum(temps) / len(temps):.1f}°C, highest {max(temps):.0f}°C, lowest {min(temps):.0f}°C "
                        f"over {len(temps)} days.")
        log = []
    log.append([today.date().isoformat(), w["main"]["temp"], w["weather"][0]["main"]])
    state.set("log", log)
    return {"days_logged": len(log)}

FAQ

Common questions

What data is logged each day?

By default the daily temperature, along with humidity, wind and a short description, can be logged. You choose which readings to keep, and each day's values are stored together so the monthly figures can be computed.

Is this historical data from past years?

No. The record starts on the day you set it up and grows from there. Readings are collected going forward, so the first monthly summary covers the first month of logging. Daily collection is the cadence, and monthly figures become available after the first full month.

What stats are in the monthly email?

Average, highest and lowest temperature, number of days below freezing, rainy days and the warmest and coldest dates. Other statistics, such as total rainfall, can be added if the daily data includes them. Rainfall totals need the daily readings to include precipitation, which can be arranged.

What permissions does it need?

API key. Nothing else in your accounts is used.

Does it need AI?

No. It runs without AI, so it doesn't use your plan's AI allowance.

How many runs does it use?

One run each time it checks. Checks that find nothing new and stop right away aren't counted.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

The moment it happens