Space Junkyard Gardener: A calmer way to explore orbital clutter
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady
What I Built
Space Junkyard Gardener turns satellite-catalogue data into a small, interactive garden around Earth. Instead of opening a dense catalogue and trying to make sense of rows of names and measurements, you can explore a 3D scene, inspect objects, and get a plain-language report about the current view.
The project is for curious learners and space enthusiasts who want an approachable overview without having to parse raw catalogue data first. The scene is illustrative: marker positions are decorative, and the app does not calculate orbits, collisions, or risk.
Demo
Demo video: [Add a link to a short video of the app running locally with Ollama]
The Vercel version is not deployed yet. It uses sample data and fallback summaries; the local Ollama report feature requires running the app on your own machine.
Code
How I Built It
The app is built with plain HTML, CSS, and JavaScript, plus a small Node.js server. The server fetches and caches CelesTrak SATCAT data. For report writing, it can call Llama 3.2 3B through Ollama running locally. If Ollama or the catalogue is unavailable, the app falls back to clearly labelled sample data and a plain summary.
The model writes the natural-language report; it does not calculate orbital positions or collision risks.
Why Does Open Innovation Matter?
Running the model through Ollama lets the report feature work on my own machine without a hosted model API key. I can change the model, inspect how the prompt is used, and keep the report request on the local server. The catalogue fetch still needs internet access, but the built-in sample keeps the app usable when the catalogue cannot be reached.
My Agent Session
Not included.
The Lazy Payoff
The app saves the first bit of effort: finding a manageable set of catalogue objects and turning them into something easier to browse. Instead of starting with raw rows, you can look around the scene and ask the local model for a short explanation. I haven’t measured time saved with users yet.
Prize Categories
No partner categories.
Top comments (0)