pace Junkyard Gardener: A Calmer Way to Explore Orbital Clutter

Prashant Kumar — Mon, 26 Oct 2026 18:53:33 +0000

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

GitHub repository

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.

Receiptory: Track receipts privately with local AI

Prashant Kumar — Mon, 19 Oct 2026 17:57:22 +0000

Receiptory — private receipt tracking with local AI

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle.

What I Built

Receiptory helps freelancers and small businesses track expenses and organize receipt details.

You can add, edit, search, and organize expenses. In the full local version, you can also select a receipt image or PDF. The browser reads the file and runs OCR. A local AI model suggests the merchant, date, total, currency, and category. You can review and edit the suggestions before saving; nothing is saved automatically.

A one-time license is an idea I would test with freelancers, not a price I have validated with customers.

The hosted demo is a static version. It supports manual expense tracking, but AI suggestions and local accounts require running Receiptory on your computer with Ollama.

Demo

Hosted demo: https://receiptory.vercel.app/
Full local version: Install Ollama, download a model such as qwen2.5:3b, then run node server.js. Open http://localhost:8000 and create a local account.

The browser downloads OCR and PDF-reading assets from CDNs on first use. Once Ollama, a model, and the browser assets are available, the full workflow can run without a cloud AI service.

Code

GitHub repository: https://github.com/Prashantkumar975/Receiptory

Receiptory uses plain HTML, CSS, and JavaScript, plus a small Node.js server with no npm package dependencies.

How I Built It

The browser uses Tesseract.js for OCR and PDF.js to render up to the first three pages of a PDF. The local Node.js server sends the extracted text to Ollama running on the same computer. I used the open-weight Qwen2.5 3B model.

The model returns expense details and marks fields that are missing or uncertain. Receiptory displays them in an editable form. The user must confirm a draft before it is saved.

Receipt files are read in the browser; there is no receipt upload endpoint. OCR text is sent to the local server and Ollama. Expenses are stored in the browser’s local storage.

Local accounts use scrypt-hashed passwords with per-user salts. Sessions use random tokens stored in server memory and expire after seven days; restarting the server signs users out. The account feature separates data within a browser profile, but it is not operating-system-level security.

Why Does Open Innovation Matter?

Local, open-source tools support Receiptory’s privacy goal. A cloud AI service would receive the receipt text. With browser OCR and Ollama running locally, users can process receipts without sending that text to a cloud AI provider.

Local inference also avoids a per-receipt API charge, though users still need hardware and electricity to run the model. Users can choose compatible models, and the review form helps catch mistakes instead of saving uncertain suggestions automatically.

devchallenge #hf26challenge

DEV Community: Prashant Kumar

pace Junkyard Gardener: A Calmer Way to Explore Orbital Clutter

Space Junkyard Gardener: A calmer way to explore orbital clutter

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

The Lazy Payoff

Prize Categories

Receiptory: Track receipts privately with local AI

Receiptory — private receipt tracking with local AI

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

devchallenge #hf26challenge