Skip to content

Repository files navigation

🧹 MacClean AI

Python macOS AI Powered License Status

Demo

AI-powered Mac disk cleaner. Scan smarter, clean faster.
Built with Python + Groq AI · macOS native look · No subscription required


⬇️ How to Download & Open (No Technical Experience Needed)

You don't need to know how to code. Just follow the steps below.


Step 1 — Download the App

  1. Look on the right side of this page for the "Releases" section

  2. Click on the latest release (e.g. MacClean AI v1.0.0)

  3. Click on MacClean-AI-v1.0.zip to download it

    Or go directly to: github.com/crisgea71/macclean-ai/releases


Step 2 — Install & Open the App

  1. Go to your Downloads folder
  2. Double-click MacClean-AI-v1.0.zip — it unzips automatically
  3. You'll see MacClean AI.app (broom icon)
  4. Drag it into your Applications folder (just like any other app)

⚠️ First-time setup — removing the macOS security block

macOS blocks apps downloaded from the internet by default. You need to do this once, right after moving the app to Applications.

Step 1 — Open Terminal

Press Command (⌘) + Space on your keyboard → type Terminal → press Enter

A window with a black or white background opens. That's Terminal — don't worry, you just need to paste one line.

Step 2 — Paste this command and press Enter

xattr -cr /Applications/"MacClean AI.app"

Copy the line above exactly, paste it into Terminal, and press Enter. Nothing will appear on screen after — that's normal, it means it worked ✅

Step 3 — Open the app

Go to your Applications folder and double-click MacClean AI.app. It will open normally, with no warning. You never need to do this again.


Why does this happen?
macOS automatically blocks apps that don't have a paid Apple Developer certificate ($99/year). The app is safe — the command above simply tells macOS to trust it on your computer.


Step 3 — Get a Free Groq API Key

MacClean AI uses AI features powered by Groq — a completely free service.

  1. Go to console.groq.com
  2. Create a free account (or sign in with Google)
  3. Click "Create API Key", give it a name, and copy the key (it looks like: gsk_abc123...)
  4. Open MacClean AI → click ⚙ Settings → paste the key in the Groq API Key field → Save

Step 4 — Use the App

  1. Click "Choose Folder" and select a folder on your Mac (e.g. Downloads, Documents)
  2. Click "Scan" — takes a few seconds, with a live progress counter
  3. Review what the app found:
    • Duplicate files
    • Heavy folders (node_modules, .venv)
    • Cache and temp files
    • Old installers (.dmg, .pkg)
    • Old screenshots
    • Broken symlinks
  4. Check the items you want to delete
  5. Click "Delete Selected" and confirm

That's it. The AI explains what it found in plain English.


💡 Why Use MacClean AI?

Most people never clean their Mac because it's boring, slow, and risky — you don't know what's safe to delete.

With MacClean AI you just:

  1. Pick a folder
  2. Click Scan
  3. Read what the AI found
  4. Check what you want to delete
  5. Click Delete Selected

No Terminal. No technical knowledge. No guessing.


🔒 Safety First

MacClean AI is built around one principle: you are always in control.

  • Nothing is deleted automatically — every deletion requires your manual selection
  • Confirmation dialog before any file is removed
  • System folders are never touched — only the folder you choose gets scanned
  • Large files and old files are info-only — shown but never pre-selected for deletion
  • AI gives suggestions, not commands — final decision is always yours

⏱️ Time Saved vs. Doing It Manually

Task Manual MacClean AI
Find duplicate files 45–90 min < 30 seconds
Hunt down old installers 20 min < 10 seconds
Find & delete cache/temp files 30 min < 10 seconds
Spot duplicate PDFs 60 min < 30 seconds
Find broken symlinks Impossible without Terminal automatic
Find heavy node_modules/.venv 15 min < 10 seconds
Total ~3 hours ⚡ under 2 minutes

✨ What It Finds

Category What it finds Deletable
🔁 Duplicate Files Identical files taking up space twice
📄 Duplicate PDFs Same PDF saved in multiple locations
📦 Old Installers .dmg, .pkg, .exe you forgot about
📸 Old Screenshots Screenshots older than 1 day ✅ auto-selected
🗑 Cache & Temp .DS_Store, __pycache__, .tmp ✅ auto-selected
🔗 Broken Symlinks Dead links pointing to nothing ✅ auto-selected
⚠️ Heavy Folders node_modules, .venv from old projects
💾 Large Files Files over 500 MB 👁 info only
🕐 Old Files Not modified in 6+ months 👁 info only

🤖 AI Features (powered by Groq)

  • Auto-summary — after every scan, AI explains what it found in simple terms
  • Safe-to-delete suggestions — AI tells you what's risky and what's safe
  • Chat assistant — ask anything: "What is pycache?", "Is this .dmg safe to delete?"
  • Powered by llama-3.3-70b-versatile via Groq (free tier available)

💳 Free vs Pro

Feature Free (2 scans) Pro
All scan categories
AI summary & chat
Delete selected files
Unlimited scans

Pro → contact the developer for a license key


🛠 For Developers — Run from Source

# 1. Clone the repo
git clone https://github.com/crisgea71/macclean-ai.git
cd macclean-ai

# 2. Create virtual environment
python3 -m venv .venv
source .venv/bin/activate

# 3. Install dependencies
pip install -r requirements.txt

# 4. Run
python3 main.py

🗂️ Project Structure

macclean-ai/
├── main.py          # UI + entry point (customtkinter)
├── scanner.py       # Scan logic (duplicates, cache, PDFs, symlinks...)
├── cleaner.py       # Delete logic
├── ai_engine.py     # Groq API integration
├── config.py        # API key + license/trial management
├── requirements.txt
└── dist/
    └── MacClean AI.app   # Packaged app

🛠 Tech Stack

Tool Purpose
Python 3.11+ Core language
customtkinter Modern UI
Groq SDK AI integration
pathlib File operations
PyInstaller .app packaging

📄 License

Free for personal use · Pro license for unlimited scans
© 2025 MacClean AI — Built with ❤️ and AI

About

AI-assisted macOS cleanup tool that scans folders for duplicates, cache files, old installers, screenshots and heavy folders.

Topics

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages