GitHub - jwardbond/forecats: Daily cat pictures on your home assistant server

Wake up every morning (more) excited to look at the forecast! This is a custom Home Assistant integration which uses forecast data, pictures of your pets, and Google's Nano Banana API to generate and serve weather-themed drawings of your precious babies every morning.

Blog post here.

Features

• Home assistant integration to generate pictures
• Customizable automation template to control drawing styles, generation times, etc.
• Optional optimization for E-ink screens (currently limited to spectra6 panels)

Examples

You can display it on an e-ink screen

Or on your HA Dashboard

Works in better weather

Getting Started

Requirements

• A home assistant server with the following add-ons
  • File editor add-on
  • Terminal and ssh add-on
  • Meteorologisk institutt (Met.no) integration
• A google AI studio API key. Note that, as of writing, you need to input billing details to get the free credits.

Setup

Option A: Install via HACS (recommended)

1. Install HACS if you haven't already.
2. In HACS, click Custom repositories and add https://github.com/jwardbond/forecats with category Integration.
3. Search for "Daily Forecats" in HACS and install it.
4. Restart Home Assistant, then continue from step 2 below.

Option B: Manual install

Do the following in your HA server, using the Terminal & SSH addon, or docker exec if you are running a container on a host system

1. Create the necessary directory structure in your Home Assistant server:

mkdir -p /config/custom_components && mkdir -p /config/forecats_data/input_images

2. Download and copy the integration files

cd /tmp && git clone https://github.com/jwardbond/forecats.git && cp -r forecats/custom_components/forecats /config/custom_components/

2. Select and upload pet images using one of the following workflows:

Option 1 — Media Browser (no SSH required, recommended for new users)

• In HA, go to Media > Local Media and create a folder called forecats.
• Upload your pet photos directly from the browser.
• In the blueprint, set Input image directory to /config/media/forecats and leave Input image paths blank.

Option 2 — Legacy directory (existing users)

• If you already have images at /config/forecats_data/input_images/, no change needed.
• Set Input image directory to /config/forecats_data/input_images/.

Option 3 — Explicit paths

• Provide a list of exact file paths via Input image paths (useful when you want fine-grained control over which images are used).
• input_image_dir and input_image_paths can be used together; images from both sources are merged.

In all cases: choose clear photos of your pets and rename the files so the pets' names are in the filenames.

3. Enable the custom integration by adding forecats: to your configuration file:

# configuration.yaml

default_config:

# ...existing data

automation: !include automations.yaml

forecats:

5. Set up the automation using one of the following options:

Option A: Blueprint (recommended)

• Go to Settings > Automations & Scenes > Blueprints and click Import Blueprint.
• Paste the URL: https://github.com/jwardbond/forecats/blob/master/blueprints/automation/forecats/forecats.yaml
• Create an automation from the blueprint and fill in your details.

Option B: Manual

• Copy the automation template into config/automations.yaml.
• Fill out or remove any <> placeholders.

6. Restart your server

That's it! Every morning at 5:00 am, the forecats integration will generate the following images in the config/www/daily_forecats/ directory:

• forecats_original.png: the unprocessed output image from Gemini
• forecats_optimized.png: the output image cropped to your desired size and adjusted for display on your screen (currently only supports color adjustments for Spectra6 e-ink)

These images should be accessible on your local network at (e.g.): <YOUR HA URL>/local/daily_forecats/forecats_original.png

Local Testing

I got annoyed testing out new prompts on HA, so I made a folder to experiment locally. If you would like to use it:

1. Clone the repo and enter the testing folder:

git clone https://github.com/jwardbond/forecats.git && cd forecats/local_testing

1. Add your cat images to the forecats_data/input_images folder.
2. Create a .env file with your Gemini API key.
3. Copy the data from your automation into test.py.
4. Run:

(Optional) Sending to an e-ink screen

You will need a screen controllable with ESPHOME. I used seeed studio's e10002 spectra6 display. I've included the esphome config I use here. The basic idea is to set the automation to run every day at a 5:00 am, and have the screen wake up every day slightly before that, download the picture at 5:01 am (to leave time to generate), and then go into deep sleep until the next day.

TODO

• Enrol in HACS for easier install
• Option to save images to dir
• Make automation into blueprint for easier install
• Separate e-ink instructions
• See if I can make it more configurable from GUI
• Support for multiple cities