Sloth Sorter: A Local AI That Organizes Your Messy Folders, Slowly (Gemma 3 + Ollama)

Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady Submission 🦥

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady

Everyone has that folder. Mine is full of Screenshot 2026-10-21 at 3.12.png, final_final_v2.docx and IMG_4821.jpg, and I have been "going to sort it" for months.

Sloth Sorter is a local web app that does the sorting for me. I point it at a messy folder, and a local AI model looks at each file and works out what it actually is. It then proposes a clean name and a category folder, so final_final_v2.docx becomes nexus-labs-design-agreement in Documents, and that Slack screenshot goes to Screenshots.

It works at a sloth's pace on purpose. Files are processed one at a time with a small pause between them, so it never hogs my laptop's GPU, and nothing moves until I review the preview and click Apply. Every run is logged, so one click undoes it.

It saves the chore I keep avoiding, and the people it suits are anyone whose Downloads folder has become a lifestyle.

"Does the chore so you don't have to. Slowly."

Sloth Sorter is an offline desktop web application that organizes messy folders using local multimodal AI ( Gemma 3:4B running via Ollama ). By processing files sequentially, one by one, with a gentle pacing delay, it brings order to chaotic downloads, desktops, and project dumps without bogging down your machine—designed specifically to run comfortably on everyday laptops with zero data ever leaving your device.

These numbers are taken directly from actual benchmark runs on the repository's 26-file test set ( sample_mess ):