NoEntropy 🗂️

AI-powered file organizer that intelligently sorts your messy Downloads folder using Google Gemini API

About

NoEntropy is a smart command-line tool that organizes your cluttered Downloads folder automatically. It uses Google's Gemini AI to analyze files, understand their content, and categorize them into organized folder structures. Say goodbye to manually sorting through hundreds of downloads!

Use Cases

• 📂 Organize a messy Downloads folder
• 🤖 Auto-categorize downloaded files by type and content
• 🔍 Smart sub-folder creation based on file content
• 🚀 Batch file organization without manual effort
• 💾 Reduce clutter and improve file system organization

Features

• 🧠 AI-Powered Categorization - Uses Google Gemini API for intelligent file sorting
• 📁 Automatic Sub-Folders - Creates relevant sub-folders based on file content analysis
• 💨 Smart Caching - Minimizes API calls with metadata-based caching (7-day expiry)
• ⚡ Concurrent Processing - Parallel file inspection with configurable limits
• 👀 Dry-Run Mode - Preview changes without moving any files
• 🔄 Retry Logic - Exponential backoff for resilient API handling
• 📝 Text File Support - Inspects 30+ text formats for better categorization
• ✅ Interactive Confirmation - Review organization plan before execution
• 🎯 Configurable - Adjust concurrency limits and model settings
• ↩️ Undo Support - Revert file organization changes if needed

Prerequisites

• Rust 2024 Edition or later
• Google Gemini API Key - Get one at https://ai.google.dev/
• A folder full of unorganized files to clean up!

Installation

1. Download Binary Download binary for your operating system(Windows, Linux or Mac)

   https://github.com/glitchySid/noentropy/releases
   

2. Give Permisson(For Linux/Mac)

     chmod +x binaryfilename
   

Run Locally

1. Clone repository

   git clone https://github.com/glitchySid/noentropy.git
   cd noentropy
   

2. Build the application

   cargo build --release
   

3. Run the application On first run, NoEntropy will guide you through interactive setup:

   ./target/release/noentropy
   

   Or manually create config file at ~/.config/noentropy/config.toml:

   cp config.example.toml ~/.config/noentropy/config.toml
   nano ~/.config/noentropy/config.toml
   

Configuration

NoEntropy stores configuration in ~/.config/noentropy/config.toml following XDG Base Directory specifications.

Configuration File Format

api_key = "AIzaSyDTEhAq414SHY094A5oy5lxNA0vhbY1O3k"
download_folder = "/home/user/Downloads"

Setting	Description	Example
api_key	Your Google Gemini API key	AIzaSy...
download_folder	Path to folder to organize	/home/user/Downloads

Getting a Gemini API Key

1. Visit Google AI Studio
2. Sign in with your Google account
3. Create a new API key
4. Copy the key to your configuration file

Interactive Setup

NoEntropy provides an interactive setup on first run:

• Missing API key? → You'll be prompted to enter it
• Missing download folder? → You'll be prompted to specify it (with default suggestion)
• Both missing? → You'll be guided through complete setup

Configuration is automatically saved to ~/.config/noentropy/config.toml after interactive setup.

Usage

Basic Usage

Organize your Downloads folder with default settings:

cargo run --release

Dry-Run Mode

Preview what would happen without moving any files:

cargo run --release -- --dry-run

Custom Concurrency

Adjust the number of concurrent API calls (default: 5):

cargo run --release -- --max-concurrent 10

Combined Options

Use multiple options together:

cargo run --release -- --dry-run --max-concurrent 3

Undo Mode

Revert the last file organization:

cargo run --release -- --undo

Preview what would be undone without actually reversing changes:

cargo run --release -- --undo --dry-run

The undo feature:

• Tracks all file moves in ~/.config/noentropy/data/undo_log.json
• Shows a preview of files that will be restored before execution
• Handles edge cases (missing files, conflicts, permission errors)
• Automatically cleans up empty directories after undo
• Keeps undo history for 30 days with auto-cleanup

Recursive Mode

Organize files in subdirectories recursively:

cargo run --release -- --recursive

This scans all subdirectories within your download folder and organizes files from the entire directory tree, maintaining relative folder structure when creating categories.

Command-Line Options

Option	Short	Default	Description
--dry-run	-d	false	Preview changes without moving files
--max-concurrent	-m	5	Maximum concurrent API requests
--recursive	None	false	Recursively search files in subdirectories
--undo	None	false	Undo the last file organization
--help	-h	-	Show help message

How It Works

NoEntropy follows a five-step process to organize your files:

┌─────────────────┐
│  1. Scan Files  │ → Read all files in DOWNLOAD_FOLDER (and subdir if --recursive flag is used)
└────────┬────────┘
         ▼
┌─────────────────────────┐
│ 2. Initial Categorization │ → Ask Gemini to categorize by filename
└────────┬────────────────┘
         ▼
┌──────────────────────┐
│  3. Deep Inspection   │ → Read text files for sub-categories
│     (Concurrent)      │   • Reads file content
│                       │   • Asks AI for sub-folder
└────────┬──────────────┘
         ▼
┌──────────────────────┐
│  4. Preview & Confirm│ → Show organization plan
│                       │   • Ask user approval
└────────┬──────────────┘
         ▼
┌──────────────────────┐
│   5. Execute Moves    │ → Move files to organized folders
└──────────────────────┘

Example Terminal Output

$ cargo run --release

Found 47 files. Asking Gemini to organize...
Gemini Plan received! Performing deep inspection...
Reading content of report.pdf...
Reading content of config.yaml...
Reading content of script.py...
Deep inspection complete! Moving Files.....

--- EXECUTION PLAN ---
Plan: image1.png -> Images/
Plan: document.pdf -> Documents/
Plan: setup.exe -> Installers/
Plan: notes.txt -> Documents/Notes/
Plan: config.yaml -> Code/Config/
Plan: script.py -> Code/Scripts/

Do you want to apply these changes? [y/N]: y

--- MOVING FILES ---
Moved: image1.png -> Images/
Moved: document.pdf -> Documents/
Moved: setup.exe -> Installers/
Moved: notes.txt -> Documents/Notes/
Moved: config.yaml -> Code/Config/
Moved: script.py -> Code/Scripts/

Organization Complete!
Files moved: 47, Errors: 0
Done!

Undo Example

$ cargo run --release -- --undo

--- UNDO PREVIEW ---
INFO: will restore 5 files:
  Documents/report.pdf -> Downloads/
  Documents/Notes/notes.txt -> Downloads/
  Code/Config/config.yaml -> Downloads/
  Code/Scripts/script.py -> Downloads/
  Images/photo.png -> Downloads/

Do you want to undo these changes? [y/N]: y

--- UNDOING MOVES ---
Restored: Documents/report.pdf -> Downloads/
Restored: Documents/Notes/notes.txt -> Downloads/
Restored: Code/Config/config.yaml -> Downloads/
Restored: Code/Scripts/script.py -> Downloads/
Restored: Images/photo.png -> Downloads/

INFO: Removed empty directory: Documents/Notes
INFO: Removed empty directory: Code/Config
INFO: Removed empty directory: Code/Scripts

UNDO COMPLETE!
Files restored: 5, Skipped: 0, Failed: 0

Supported Categories

NoEntropy organizes files into these categories:

Category	Description
Images	PNG, JPG, GIF, SVG, etc.
Documents	PDF, DOC, DOCX, TXT, MD, etc.
Installers	EXE, DMG, APP, PKG, etc.
Music	MP3, WAV, FLAC, M4A, etc.
Archives	ZIP, TAR, RAR, 7Z, etc.
Code	Source code and configuration files
Misc	Everything else

Supported Text Formats

NoEntropy can read and analyze the content of 30+ text file formats:

Source Code: rs, py, js, ts, jsx, tsx, java, go, c, cpp, h, hpp, rb, php, swift, kt, scala, lua, r, m
Web/Config: html, css, json, xml, yaml, yml, toml, ini, cfg, conf
Documentation: txt, md, sql, sh, bat, ps1, log

Caching

NoEntropy includes an intelligent caching system to minimize API calls:

• Location: .noentropy_cache.json in project root
• Expiry: 7 days (old entries auto-removed)
• Change Detection: Uses file metadata (size + modification time) instead of full content hashing
• Max Entries: 1000 entries (oldest evicted when limit reached)

How Caching Works

1. First Run: Files are analyzed and categorized via Gemini API
2. Response Cached: Organization plan saved with file metadata
3. Subsequent Runs:
   • Checks if files changed (size/modification time)
   • If unchanged, uses cached categorization
   • If changed, re-analyzes via API
4. Auto-Cleanup: Removes cache entries older than 7 days

Undo Log

NoEntropy tracks all file moves to enable undo functionality:

• Location: ~/.config/noentropy/data/undo_log.json
• Retention: 30 days (old entries auto-removed)
• Max Entries: 1000 entries (oldest evicted when limit reached)
• Status Tracking: Completed, Undone, Failed states for each move
• Conflict Handling: Skips files with conflicts and reports warnings

How Undo Works

1. During Organization: Every file move is recorded with source/destination paths
2. Undo Execution:
   • Lists all completed moves to be reversed
   • Shows preview of what will be restored
   • Asks for user confirmation
   • Moves files back to original locations
   • Handles conflicts (source exists, destination missing)
   • Cleans up empty directories left behind
3. Status Updates: Marks successfully undone operations
4. Auto-Cleanup: Removes undo log entries older than 30 days

Undo Safety Features

• Preview Before Action: Always shows what will be undone before executing
• Conflict Detection: Checks if source path already exists before restoring
• Missing File Handling: Gracefully handles files that were deleted after move
• Partial Undo Support: Continues even if some operations fail
• Dry-Run Mode: Preview undo operations without executing them

Troubleshooting

"API key not configured"

Solution: NoEntropy will prompt you for your API key on first run. Alternatively, manually create ~/.config/noentropy/config.toml:

api_key = "your_actual_api_key"
download_folder = "/home/user/Downloads"

"Download folder not configured"

Solution: NoEntropy will prompt you for the folder path on first run. Alternatively, manually add it to your config:

download_folder = "/path/to/your/Downloads"

"API rate limit exceeded"

Solution:

• Wait a few minutes before trying again
• Reduce --max-concurrent to limit API calls
• Use caching to reduce redundant requests

"Network error"

Solution:

• Check your internet connection
• Verify Gemini API service is operational
• Ensure firewall allows outbound HTTPS requests

"Failed to move file"

Solution:

• Check file permissions
• Ensure destination folder is writable
• Verify source files still exist

"Cache corrupted"

Solution: Delete .noentropy_cache.json and run again. A new cache will be created.

"No completed moves to undo"

Solution: This means there are no file moves that can be undone. Either:

• No files have been organized yet
• All previous moves have already been undone
• The undo log was deleted

"Undo log not found"

Solution: No undo history exists. Run organization first to create undo log, or check that ~/.config/noentropy/data/ directory exists.

"Skipping [file] - source already exists"

Solution: A file already exists at the original location. The undo operation will skip it to prevent data loss. Manually check and resolve the conflict if needed.

"Failed to restore [file]"

Solution: Check file permissions and ensure the file exists at the destination location. Other files will continue to be restored.

Development

Build in Debug Mode

cargo build

Build in Release Mode

cargo build --release

Run Tests

cargo test

Run Clippy (Linting)

cargo clippy

Check Code

cargo check

Project Structure

NoEntropy follows a clean modular architecture for better maintainability and testability:

noentropy/
├── .github/
│   └── workflows/
│       └── rust.yml              # CI/CD workflow
├── src/
│   ├── cli/
│   │   ├── mod.rs                # CLI module exports
│   │   ├── args.rs               # Command-line argument definitions
│   │   └── orchestrator.rs       # Organization & undo orchestration
│   ├── files/
│   │   ├── mod.rs                # File module exports
│   │   ├── batch.rs              # File batch processing
│   │   ├── detector.rs           # File type detection
│   │   ├── mover.rs              # File moving operations
│   │   └── undo.rs               # Undo file operations
│   ├── gemini/
│   │   ├── mod.rs                # Gemini API module exports
│   │   ├── client.rs             # Gemini API client
│   │   ├── errors.rs             # Gemini error handling
│   │   ├── prompt.rs             # AI prompt construction
│   │   └── types.rs              # Gemini API types
│   ├── models/
│   │   ├── mod.rs                # Data models exports
│   │   ├── metadata.rs           # File metadata structures
│   │   ├── move_record.rs        # File move tracking
│   │   └── organization.rs       # Organization plan structures
│   ├── settings/
│   │   ├── mod.rs                # Settings module exports
│   │   ├── config.rs             # Configuration management
│   │   ├── prompt.rs             # Interactive configuration prompts
│   │   └── tests.rs              # Settings tests
│   ├── storage/
│   │   ├── mod.rs                # Storage module exports
│   │   ├── cache.rs              # Caching system
│   │   └── undo_log.rs           # Undo log management
│   ├── main.rs                   # Application entry point
│   └── lib.rs                    # Library exports
├── Cargo.toml                    # Dependencies and project metadata
├── Cargo.lock                    # Dependency lock file
├── config.example.toml           # Configuration template
└── README.md                     # This file

Module Overview

• cli/ - Command-line interface and orchestration logic for organizing and undoing operations
• files/ - File detection, batching, moving, and undo operations with concurrent processing
• gemini/ - Google Gemini API integration with retry logic and intelligent prompt engineering
• models/ - Core data structures for file metadata, move records, and organization plans
• settings/ - Configuration management with interactive prompts and XDG directory support
• storage/ - Persistent data layer for caching API responses and tracking undo history

Future Enhancements

Based on community feedback, we're planning:

• Custom Categories - Define custom categories in config.toml
• Recursive Mode - Organize files in subdirectories with --recursive flag
• Undo Functionality - Revert file organization changes
• Custom Models - Support for other AI providers
• GUI Version - Desktop application for non-CLI users

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• Built with Rust
• Powered by Google Gemini API
• Inspired by the endless struggle to keep Downloads folders organized

Show Your Support

⭐ Star this repository if you find it useful!

---

Made with ❤️ by the NoEntropy team