Phantom-OS

Phantom-OS is an invisible, high-performance cognitive overlay for Windows 11. Built to act as a real-time copilot during interviews, coding sessions, and meetings without ever being detected by screen-sharing or recording software.

---

🌟 Key Features

🥷 True Stealth Mode

Uses low-level Windows APIs (SetWindowDisplayAffinity) to remain 100% invisible to OBS, Zoom, Teams, Google Meet, and any other screen capture tools. Only you can see it.

🧠 Bring Your Own LLM

Native plug-and-play support for OpenAI (GPT-4o), Anthropic (Claude 3.5 Sonnet), Google (Gemini 1.5 Pro), and fully local, offline models via HuggingFace or LM Studio.

📷 DPI-Aware Active Vision

Instantly scrapes and understands code, questions, and UI elements directly from your active screen using a custom Tesseract OCR preprocessing pipeline optimized for monospaced fonts.

🎙️ Real-Time Audio Loopback

Hooks directly into Windows WASAPI to silently record internal system audio, transcribing multi-speaker meetings and spoken interview questions in real time.

⚡ Zero-Latency Global Hotkeys

Control the AI entirely via the keyboard while in-game or mid-interview. You never have to move your mouse or click away from your active window.

🛠️ Technology Stack

Phantom-OS is built for extreme performance, low resource consumption, and stealth.

• Core Framework: .NET 8 & WPF (Windows Presentation Foundation)
• Screen Processing: Tesseract.NET (LTSM OCR Engine) + Custom EmguCV/GDI+ Pipeline
• Audio Capture: NAudio (WASAPI Loopback Capture)
• Markdown Rendering: Markdig.Wpf (Dynamic Dark Mode Syntax Highlighting)
• System Integration: Native user32.dll P/Invoke (Hooks, Display Affinity)
• Security: System.Security.Cryptography.ProtectedData (Local DPAPI Encryption)

---

⌨️ Global Keybindings

Phantom-OS runs transparently over your desktop. Use these hotkeys to control it without moving your mouse:

Key	Action	Description
[	Batch Append	Snap a piece of the screen and save it to memory (Great for long coding files).
]	Batch Send	Send all batched screenshots to the AI at once.
,	Instant Capture	Take a single screenshot and instantly ask the AI to solve/explain it.
.	Audio Toggle	Start/Stop silent internal audio recording and transcription.
~	Hide / Show	Toggle the overlay visibility (content is preserved).
Ctrl+Alt+C	Copy	Silently copy the AI's last generated response to your clipboard.
F2	Reset	Clear everything and return to the home screen.
F9	Settings	Open the configuration panel to change API keys or models.

---

🚀 Installation & Setup

You can install Phantom-OS using the pre-compiled installer, or you can clone and build it yourself from the source code.

Option A: Install via Windows Installer (Recommended)

We provide a self-contained, single-click Windows Installer. You don't need to install any prerequisites.

1. Navigate to the Releases Bar in this repository.
2. Download and run PhantomOS_Setup.exe.
3. (Note: Windows SmartScreen may flag the app since it is a new, unsigned executable utilizing keyboard hooks. Click More Info -> Run Anyway).
4. Once installed, launch the app from your Start Menu.
5. Press F9 to open settings and configure your preferred LLM Provider and API Key.

Option B: Install via Git Clone (For Developers)

Want to run the code directly or modify it yourself?

Prerequisites:

• Windows 10/11
• .NET 8.0 SDK

Steps:

1. Open your terminal and clone the repository:

   git clone https://github.com/YOUR_USERNAME/Phantom-OS.git
   cd Phantom-OS

2. Run the application using the .NET CLI:

   dotnet run

3. To package the application into a standalone installer yourself, run the automated PowerShell script (requires Inno Setup 6):

   .\build_installer.ps1

---

🤝 Contributing & Open Source

Phantom-OS is completely open-source and community-driven. I built this to disrupt the market of overpriced AI wrappers and give developers a powerful, free tool.

I actively invite developers to fork this repository, fix bugs, optimize performance, and add new features.

How to contribute:

1. Fork the Project
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

Distributed under the MIT License. See LICENSE for more information.

Built with 🖤 by akashsalan