LazyDesk: A Local AI File Organizer That Saves Time

KHUSHI — Sun, 25 Oct 2026 20:31:44 +0000

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

What I Built

I built LazyDesk, a local AI-powered file organizer designed to make sorting messy folders easier.

We all have folders filled with PDFs, images, notes, and downloads. Organizing them manually takes time. LazyDesk explores how AI can help automate this repetitive task while keeping the user in control.

GitHub repository: https://github.com/thekhushicode/Lazydesk

How It Works

LazyDesk is built with Python and Streamlit. It uses Ollama and the open-weight gemma3:1b model for local AI experimentation and includes fallback rules for categorizing files.

Its key features include:

File categorization: Helps sort files into useful categories.
Demo Mode: Lets users test the workflow without moving their real files.
Move and undo: Supports file organization with an undo workflow.
Safety checks: Includes overwrite protection and path-traversal prevention.

Why Open-Source AI Matters

I wanted to experiment with AI without making a hosted AI service the only option.

Using an open-weight model through Ollama lets developers run inference locally, experiment with different models, and explore AI without necessarily paying for a remote API for every request.

Local inference can also help keep file contents on the user's machine. Privacy still depends on the application's design and configuration, so safe testing and careful file handling remain important.

For me, open AI innovation means being able to learn, experiment, and build useful tools with greater control over the technology.

Testing and Safety

I ran the automated test suite using:

python -m pytest -v

All eight tests passed, covering classification, demo files, move-and-undo behavior, overwrite protection, path safety, and supported categories.

I recommend starting with Demo Mode before trying the organizer on real files.

What I Learned

This project helped me explore local AI, Python development, and the importance of making automation safe and testable.

My goal with LazyDesk is simple: less time organizing files, more time doing useful work.

I'd love to hear how other developers are using local AI to automate small, repetitive tasks.

devchallenge #hf26challenge #python #ai #opensource #ollama #gemma