Slothsort
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady What I Built My Downloads folder had 500+ files. Half of them were named things like scan0042.txt, doc1.txt, thing.md. I had no idea what was inside without opening each one. So I built Slothsort — a tool that runs a local AI model on your laptop, reads your files, and sorts them into clean folders like…
Slothsort is an open-source AI tool developed to help users sort their files more efficiently and accurately. Facing a cluttered Downloads folder with over 500 files named in a confusing manner, the creator built Slothsort to run a local AI model on their laptop, read the files, and sort them into clean folders like Finance, Career, Code, and Study.
The tool also renames files to make more sense. The tool works by dropping files into the watched folder, clicking the Scan Directory button, and then reviewing and approving or skipping the proposed moves. Every move is logged, and each move is undoable. Slothsort is built with Python and FastAPI for the backend, SQLite for storing move history, and vanilla HTML/CSS/JS for the frontend.
It uses Google Gemma 2 (2B) running locally through Ollama for content analysis, achieving an 81% accuracy rate in sorting files, compared to 67% accuracy with extension + keyword rules. This AI tool prioritizes privacy, as it processes personal files locally on the user's machine without sending them to third-party APIs or requiring an internet connection.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
