I built a sloth-brained Downloads folder tidier that runs 100% offline

Description and use

An offline local LLM tool that automatically categorizes, renames, and moves files from the Downloads folder into a tidy structure, eliminating manual cleanup.

Problem

The Downloads folder becomes cluttered with unnamed or poorly named files, making organization a tedious chore.

Outcome

The tool runs fully offline, automatically categorizes and renames files, and logs moves for undo, eliminating manual cleanup.

Workflow

• Install Ollama and pull a model (e.g., qwen2.5:7b).
• Install Python 3.11+ (no pip packages needed).
• Edit config.toml to set folders, model, and categories.
• Run python tidier.py run for a dry run.
• Run python tidier.py run --apply to execute moves.
• Run python tidier.py watch --apply to keep the script running and tidy new downloads.
• Use python tidier.py undo to reverse the last batch.

Evidence

lazy-downloads-tidier watches the folder, reads each file, and asks a local LLM two questions: which of my categories does this belong in? and what should it be called?

Source

Install Ollama and pull a model
ollama pull qwen2.5:7b # or gemma3:4b / llama3.2:3b for less RAM

Source

Dry run by default. You must pass --apply to move anything.

Source

The tool reads my tax PDFs, contracts, and personal photos. Sending those to someone else's API to get a better filename isn't a trade I'd make. With a local model, the files never leave the disk.

Source