Digital Janitor
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built I built Digital Janitor , a local-first AI tool that helps my friend organize their messy Downloads folder. It uses AI to classify files, suggest folders, explain its decisions, and safely organize them without permanently deleting anything. Demo [ADD DEMO VIDEO LINK] Code [ADD GITHUB LINK] How I Built…
This submission for the Hacktoberfest Weekend Challenge introduces Digital Janitor, an AI-powered tool designed to assist a friend in organizing their cluttered Downloads folder. The application utilizes AI to classify files, propose appropriate folders, provide explanations for its decisions, and safely reorganize the files without permanently deleting any data.
Developed using Python, Ollama, and Gemma, Digital Janitor operates locally on Windows systems. The AI analyzes file metadata on the user's own computer and recommends an optimal organizational structure. The application also incorporates a safe file manipulation system, allows users to experience the tool in demo mode, and includes a "Mess Score" metric to quantify the level of disorganization in the user's Downloads folder.
Open innovation plays a crucial role in this project, as sensitive personal files are kept secure by avoiding the upload of data to cloud-based AI services. By leveraging Ollama and an open-weight model, Digital Janitor can run locally on the user's computer, ensuring data privacy and enabling the AI to be upgraded or modified without requiring a complete reconstruction of the application around a proprietary API.
The "Gemma" category recognizes the best use of the Gemma model, which serves as the local AI intelligence behind Digital Janitor.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
