SlothSort：主打本機 AI 的檔案整理工具

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

What I Built

🦥 SlothSort — A Local AI File Organizer

What if organizing files didn't require endless manual sorting?

SlothSort is a Python-based file organizer that explores how local AI can make everyday file management simpler. Instead of spending time sorting a cluttered folder, users can scan files, categorize them by extension, identify potential duplicates, and review organization suggestions before approving file moves.

I built SlothSort around one simple principle: let AI do the repetitive thinking, but keep the user in control.

✨ Key Features

• 📂 File Categorization: Organizes files into categories based on their extensions.
• 🤖 Local AI Suggestions: Uses Ollama with Qwen 2.5 1.5B to generate filename suggestions.
• 🔍 Duplicate Detection: Uses SHA-256 hashes to identify files with identical contents.
• 👀 Preview Before Action: Lets users review proposed file moves before applying them.
• 🛡️ User-Controlled Workflow: Keeps file organization deliberate rather than silently changing files.

The goal is to help students, developers, and anyone with cluttered folders spend less time organizing files manually.

Demo

The project runs locally through Streamlit.

Code

The project is built with Python and Streamlit, with a locally running Ollama model for AI-powered suggestions.

Contributions, suggestions, and improvements are welcome!

How I Built It

I built SlothSort using Python, Streamlit, and Ollama.

The AI component uses Qwen 2.5 1.5B, an open-weight language model that can run locally through Ollama. The application communicates with Ollama's local API to request filename suggestions.

The workflow combines several components:

1. Scanning: Reads files from a user-selected folder.
2. Categorization: Groups files based on their extensions.
3. Duplicate Detection: Calculates SHA-256 hashes to compare file contents.
4. AI Assistance: Requests filename suggestions from the local language model.
5. Review and Organization: Presents proposed file moves for the user to review before applying them.

Streamlit provides the interface, while Python handles file processing and organization logic.

The idea was to combine deterministic programming for tasks such as categorization and hashing with AI assistance for tasks that benefit from language understanding.

Why Does Open Innovation Matter?

Open innovation makes experimentation more accessible.

Using an open-weight model with local inference allowed me to explore AI integration without depending on a paid, cloud-hosted language-model API for every suggestion.

It also gave me the opportunity to learn how model runtimes, Python applications, and local APIs work together.

For a file organizer, local inference offers an additional privacy advantage: model processing can happen on the user's computer instead of sending prompts to a remote AI service. The application's complete data flow still needs to be reviewed before handling sensitive files.

Most importantly, open tools make it easier for developers to inspect, experiment with, adapt, and improve the technology they use.

I want SlothSort to reflect that spirit: useful, approachable, and open to improvement.

The Lazy Payoff

The idea behind SlothSort is simple: spend less time sorting files and more time doing what matters.

Instead of manually checking every filename or searching for identical files by eye, users can use automated categorization and hash-based duplicate detection to reduce repetitive work.

I haven't measured a reliable time-saving figure yet, so I won't claim a specific number. My next step is to test SlothSort with realistic folders and compare the time required with manual organization.

Because sometimes the smartest productivity improvement is making a repetitive task a little less repetitive. 🦥

Prize Categories

Select only the partner prize categories that your project actually qualifies for, based on the official challenge rules.

• Open-source AI / local inference — if this matches an eligible category in the challenge.

Final Thoughts

SlothSort is my exploration of the Slow and Steady theme: a small, practical application that combines local AI with predictable file-processing logic.

I believe AI tools should help people work smarter without taking away their control.

Slow and steady. One folder at a time. 🦥

I'd love to hear your suggestions for making SlothSort more useful!