SlothSort

A developer built SlothSort, an open-source file-sorting tool that watches a folder, reads each file's contents with a local open-weight model served through Ollama, and renames, files, and archives items without sending data off the machine. The tool uses watchdog to queue new files, returns a structured name/folder/confidence result, leaves low-confidence files untouched, and supports a one-command undo.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady https://dev.to/challenges/hacktoberfest-week3-2026-10-19 SlothSort is a lazy person's file butler. It watches your Downloads folder or any folder you point it at , reads what's actually inside each file, and then renames it with a sensible name, sorts it into the right folder, and archives anything stale, all by itself and all on your own machine. No more Screenshot 2026-10-12 at 11.42.07 3 .png , final FINAL v2.pdf , or a Downloads folder with 900 mystery files. You drop things in, SlothSort files them away overnight, and in the morning you get a short digest of what it moved and why. If it isn't confident about a file, it leaves it alone and flags it, and every move can be undone with one command. Anyone who has ever said "I'll clean this up later" gets to be a little lazier. Add your GitHub repo link here. On DEV you can embed it directly with the {% embed https://github.com/your-username/slothsort %} tag. SlothSort is built around a local open-weight model served through Ollama , so the whole pipeline runs without a network connection. watchdog that notices new files and queues them. { "new name": ..., "folder": ..., "confidence": ... } . slothsort undo can reverse it. The folder rules live in a plain config file, so changing how SlothSort behaves means editing a few lines, not retraining anything. Sorting your files means the tool has to read your files : tax documents, invoices, medical reports, private screenshots. That is exactly the kind of data I don't want to send to a server I don't control. Running an open-weight model locally made that possible: For a "set it up once and forget it" tool, that reliability matters as much as the privacy. Optional: embed your DevRelay session here with the agent session tag, or paste a link to it. Replace these with your real numbers, or delete this section if you'd rather not include it.