Urgent.News

What's breaking now, across thousands of outlets.

AI

What If Our Desktop Had Its Own Little AI Companion? Meet Luna

This is a submission for the MLH x DEV Writing Challenge Meet Luna ๐Ÿฑ What I Built My husband and I have always liked those little animated desktop pets โ€” the tiny characters that move around your screen and make your computer feel a little more alive. One day, we started talking about them and wondered: What if we could make something like that, but instead of just moving around the screen, itโ€ฆ

This is the story of a little AI desktop companion named Luna. The concept came from a husband and wife who enjoy animated desktop pets and wondered if they could create something that offered more practical help. Luna aims to be a more natural way for users to interact with AI by bringing it closer to their work on the desktop.

Building Luna required combining two elements: the fun of an animated desktop pet and the utility of an AI assistant. The application was created using Electron, React, and TypeScript, with Google's open-weight Gemma AI model powering its AI experience. Electron facilitated the creation of a desktop app, while React and TypeScript managed the interface and logic. Gemma was integrated via Google's GenAI tooling to allow users to chat with Luna.

However, turning this idea into a real product was more complex than imagined. Ensuring communication between separate desktop windows, routing messages correctly, and reliably handling AI responses required extensive debugging. These challenges taught valuable lessons about the importance of interaction, interface design, and the finer details in building AI products.

Gemma was chosen for its potential in a real desktop setting rather than just another chatbot interface. The allure was in integrating an AI model into an already familiar experience, making AI feel more like a companion rather than just a tool accessed through a browser. Luna's next steps involve improving its personality, enhancing everyday interactions, and enabling it to assist with tasks more naturally by understanding what's happening on the screen.

Ultimately, Luna aims to evolve from a cute character on the desktop to a genuinely useful AI companion, combining charm with practical assistance. This project taught the reporter that even small, enjoyable ideas can lead to significant learning experiences. The reporter is eager to continue developing Luna and explore its potential further.

Written by urgent.news from Dev.to's reporting โ€” not their text. Machine-written โ€” may contain errors; check the original before relying on it.

Read the original at dev.to โ†’

More in AI

Logistic Regression

When you start your journey in Machine Learning, the first algorithm you usually learn is Linear Regression. Linear regression draws a straight line using the equation: y = m x + c This straight lineโ€ฆ

  • Logistic Regression is foundational in Machine Learning, learned post Linear Regression
  • Predicts binary outcomes like student placement (1) or not (0) based on exam scores
  • Converts raw scores into probabilities between 0 and 1 using Sigmoid function

Pocket Trail: an open-weight model writes you a walk, then tells you to close the tab

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Most "get outside" apps want you to stay inside them. Pocket Trail does the opposite.

  • Pocket Trail generates personalized trail cards based on user's desired duration and type of walk.
  • App considers factors like weather, daylight, and moon phase for tailored experience.
  • Open-weight model writes trail descriptions for the app.

More from Saturday 10 October โ†’