SlothOps AI：讓 AI 整理檔案，讓用戶放慢步調

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

What I Built

Meet SlothOps AI — a local-first AI-powered file organizer built around one simple idea: spend less time managing files and more time doing meaningful work.

Downloads folders and document directories can quickly become messy. Finding the right file, understanding unfamiliar documents, grouping related content, and spotting duplicates can turn into repetitive work.

SlothOps AI aims to make that workflow easier. It helps users:

• Ingest and analyze supported local text and Markdown files.
• Use AI-assisted analysis to suggest meaningful categories and extract useful information.
• Review suggested file-organization actions before applying them.
• Identify potential duplicate files.
• Keep an activity history and support undo workflows.
• Organize files through a safety-conscious workflow that preserves original files instead of automatically deleting them.

The goal isn't to hand over control of your filesystem to an AI. It's to let AI handle the tedious thinking while you stay in control of the final action.

Demo

Try SlothOps AI: https://nikhilraman12-slothops-ai-app-zfoqb6.streamlit.app/

For the local-first inference experience, the project is designed to work with Ollama and an open-weight Gemma model.

Code

GitHub repository: https://github.com/NikhilRaman12/SlothOps-AI

The repository includes the Streamlit application, modular Python components, AI-engine logic, file-operation safeguards, history management, tests, and project documentation.

If you care about practical AI tooling, local inference, or safer automation, contributions and feedback are welcome!

How I Built It

The project brings together a lightweight Python application stack and open-weight AI.

• Python — application logic and file processing.
• Streamlit — interactive user interface.
• Ollama + Gemma — local model inference for AI-assisted analysis.
• SQLite — activity-history persistence.
• Pytest — automated testing of core components.

I separated the application into focused modules for ingestion, AI analysis, file operations, and history management. This keeps the project easier to maintain and makes it possible to test important behavior independently.

The workflow emphasizes a human-in-the-loop design:

1. Inspect supported files.
2. Generate analysis and organization suggestions.
3. Review the proposed actions.
4. Apply the actions only when ready.
5. Track activity and use the available undo workflow when appropriate.

I also explored adapter modules for external data sources, keeping potential integrations modular rather than tightly coupling them to the core application.

The guiding principle was simple: AI should make routine work easier without making file operations unpredictable.

Why Does Open Innovation Matter?

Open innovation matters because useful AI shouldn't require every developer to depend on a proprietary API or send private document contents to a remote model provider.

Open-weight models and tools such as Ollama give developers more control over how AI is run, tested, and integrated into their workflows.

For a file organizer, that control is especially important. Documents can contain personal notes, research, work materials, or sensitive information. A local-inference architecture provides a path toward analyzing supported files on the user's own machine.

Open-source development also makes the implementation inspectable. Developers can examine the safeguards, adapt the workflow, test alternative models, and contribute improvements.

SlothOps AI is my exploration of a more practical relationship between AI and everyday computing: less repetitive work, more user control, and more freedom to build.

The Lazy Payoff

The best automation is the kind that quietly removes friction from your day.

Instead of manually reviewing every document and deciding where it belongs, SlothOps AI can help generate organization suggestions for you to inspect and apply.

The potential payoff is less repetitive sorting, a more understandable file collection, and more time for actual work.

I'm treating time saved as something to measure through real usage rather than inventing a number. A useful next step is to benchmark the time needed to organize the same collection manually versus with SlothOps AI.

Prize Categories

This project is submitted for the Hacktoberfest Open-Source AI Challenge — Week 3: Slow and Steady.

I'll select any additional partner prize categories only where the project meets the official eligibility requirements.

Built with Python, Streamlit, open-weight AI, and a belief that a little automation can make everyday work feel lighter.

Explore the demo. Inspect the code. Share your feedback.