TeachMyPC: I wanted file automation without giving AI control of my Mac
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle . What I Built I have a habit of letting files pile up in my Downloads folder. PDFs, screenshots, random documents... and eventually I have to sit down and organize everything. As a developer, I could write a script for that. But I don't really want to write and maintain a script every time I need something…
The user created an app called TeachMyPC to simplify file organization on a Mac. The app allows users to input instructions in plain English or Arabic and convert them into reusable rules, such as moving new PDF files from one folder to another. TeachMyPC uses a local AI model, specifically Gemma, to interpret the user's instructions and generate a structured rule.
The user can review, edit, and test the rule before enabling it. After enabling, the app monitors the specified folder and automatically handles matching files based on the set rule.
Key features of TeachMyPC include creating automation rules using natural language, moving, copying, and renaming files, filtering new files by extension, reviewing and editing AI-generated rules, testing rules with a Dry Run before execution, enabling and disabling rules, and viewing automation activity and results. The app is built with Angular and Tauri, using Rust for native filesystem access and file watching. Local AI interpretation is handled by Ollama and Gemma 3 4B.
The app targets users who frequently deal with repetitive files, such as freelancers, designers, photographers, and small businesses. These users often need a simple solution to handle small file-related tasks without having to write and maintain scripts. TeachMyPC aims to provide that simple, paid desktop utility, potentially with a one-time license rather than a monthly subscription. The user plans to explore pricing options after validating interest with potential customers.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
