Dark Sky Walk
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Dark Sky Walk : an offline night-sky companion that gets people out of the house after sunset. Most stargazing apps keep you staring at the phone, and they break down where it matters most: dark spots with no signal. Dark Sky Walk flips that. Before you leave, you ask in plain language, "What can…
Dark Sky Walk is an offline night-sky companion app designed to encourage people to leave their houses after sunset and explore the stars. Unlike traditional stargazing apps that keep users staring at their phones, Dark Sky Walk aims to bring them outside. Before leaving, users ask the app, "What can I see tonight, and where should I go?"
The app then determines what is visible (planets, moon phase, bright stars, meteor showers), checks for cloud cover and moonrise, and suggests a short walk to a nearby darker location. Upon arrival, the screen displays a simple checklist with red-light, low-brightness cards for each celestial target, and optional spoken prompts to keep users focused on the sky.
The app is ideal for beginners unfamiliar with constellations, families seeking an evening activity, and outdoor enthusiasts like hikers or campers who want to utilize clear nights without signal. Developed using a local language model, open astronomy data, and an agent framework, Dark Sky Walk operates completely offline, ensuring uninterrupted stargazing where cellular service is unavailable.
By keeping all data and models locally stored, the app remains functional on any device without a connection, safeguarding privacy and eliminating reliance on costly API fees. The open-source nature allows users to adapt the app to their preferences, whether by refining explanations for younger audiences or tailoring suggestions for specific celestial events.
Above all, Dark Sky Walk upholds the integrity of astronomical data through the use of reliable open ephemeris information, ensuring accurate and trustworthy stargazing experiences.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
