Skip to main content

Run locally

Sky AI Forecast has no build step and no dependencies to install. All you need is a modern browser.
1

Clone the repository

git clone https://github.com/m20prs/Sky-AI-Forecast.git
cd Sky-AI-Forecast
2

Open index.html in your browser

On macOS:
open index.html
On Linux:
xdg-open index.html
On Windows:
start index.html
The app opens directly from the filesystem — no local server required.
3

Search for a city

Type any city name (e.g. Tokyo) into the input field and click Check Weather.
4

Explore the forecast views

After the results load, use the three tabs to switch between views:
TabFunction calledWhat it shows
CurrentshowCurrent()Live temperature and humidity
24h Forecastshow24h()Hour-by-hour forecast for the next 24 hours
16-Day Outlookshow30d()Daily high temperatures for up to 16 days
If your browser blocks fetch() calls from file:// URLs due to CORS restrictions, serve the files with any static server:
npx serve .
Then open http://localhost:3000 in your browser.

Project structure

The entire app consists of three files:
FilePurpose
index.htmlApp markup — input, buttons, and display containers
style.cssAll visual styling and the logo arc animation
script.jsAll logic — geocoding, weather fetching, and view rendering

Deploy to the web

1

Push to GitHub

git push origin main
2

Enable GitHub Pages

Go to your repository Settings → Pages. Under Source, select Deploy from a branch, choose main, and set the folder to / (root). Click Save.
3

Visit your site

GitHub will publish the app at https://<your-username>.github.io/Sky-AI-Forecast/. It may take a minute to deploy.
Because the app makes API calls to Open-Meteo directly from the browser, there is no backend to configure. Any static hosting platform works.

Build docs developers (and LLMs) love