Google released the code for Glanceboard, a home application with AI illustrations on an e-ink display
Google open-sourced Glanceboard, an application by an employee named Raph. The application connects Google Calendar and the weather, uses the Nano Banana model to generate illustrations of children dressed for the forecast, and displays them on a local e-ink display without the cloud.
Google released the code for Glanceboard as open source. The application was created by Raph, a creative technologist at Google. The application was built using the Gemini 3.6 Flash model and the Nano Banana model.
Every morning, Glanceboard checks the family Google Calendar and the local weather forecast, then asks the Nano Banana model to generate a personalized illustration of Raph's children dressed for the forecast weather. The image is then shown on an e-ink display, so the family can see the day's schedule, what to wear and what to pack.
According to Google, the application runs on a lightweight local server without requiring cloud accounts or glowing screens. The company describes it as a calm and personalized way to organize the day; Raph says this approach also works well for involving children without the stress of notifications.
Google published the application source code, including a build guide and a list of the hardware used, in a GitHub repository and mentioned the option of having a similar application built using Google Antigravity. You can find details in the source article.
Why it matters
It shows a concrete example of how to combine a multimodal image generation model (Nano Banana) with a language model (Gemini 3.6 Flash) and local hardware into a working home tool without relying on the cloud and without a paid subscription. Because both the code and the hardware guide are publicly available on GitHub, anyone can replicate the project or adapt it to their own family organization needs.
Two audiences, two different impacts
What this means
For individuals
Anyone interested in home AI projects can download the open-source code and use the included guide and hardware list to build their own device that displays a schedule and recommended clothing based on the weather on an e-ink display without the cloud.
For a business
The project serves as a public example of how Google combines Gemini 3.6 Flash and Nano Banana models with Google Antigravity to quickly build a "vibe-coded" local application connected to hardware, which may inspire teams looking for an example to follow for similar rapid prototypes without relying on the cloud.
DevelopmentCheck the original
Event sources
clearly official source · 1 publisher, 0 independent. We count feeds from the same owner only once.