Lazy Tidier: I Taught an Open-Weight Model to Clean My Downloads Folder
说明与用途
Lazy Tidier 是一个 Python CLI,使用扩展规则和开放权重 LLM 对下载文件夹进行分类。它安全、支持 dry‑run、撤销,并保护隐私。
问题
The author’s Downloads folder was cluttered with mixed file types and ambiguous names, making manual cleanup tedious.
结果
On a 19-file test set, 11 files were processed by the LLM and all categories matched manual review; dry-run completed in ~8.6s.
工作流
- Scan folder non-recursively
- Apply extension-based rules to obvious files
- Send ambiguous PDFs, TXT, MD, DOCX to open-weight LLM with filename and up to ~500 chars
- Validate LLM JSON response, sanitize names, enforce privacy guard
- Generate dry-run plan and display table
- If --apply, write undo log and move files into category subfolders
- If --undo, reverse last apply using undo log
证据
Lazy Tidier is a Python CLI that sorts a messy folder using simple rules first and an open-weight model only for ambiguous files.
Most of the work needs no AI at all. Rules based on file extension sort the obvious files for free.
Only the ambiguous ones (PDFs and text notes) go to an open-weight model.
A normal run is a dry-run: it only prints what it would do.
--undo reverses the last run, restoring the original names too.
The privacy guard: files whose names contain any of 14 sensitive whole words are sorted locally and never sent to the model.
On my 19-file test folder, 11 files went to the model and the rest were sorted locally. The whole dry-run took about 8.6 seconds in one run.
- 记录日期: 2026-10-22T04:11:25.894Z