Magic Cursor is a premium, lightweight Windows productivity tool inspired by the concept of Google's Chromebook/Googlebook "Magic Pointer" implementation. Re-imagined and engineered from the ground up for Windows 10/11 using C# and WinUI 3, Magic Cursor lets you trigger advanced on-screen actions using local OCR (Optical Character Recognition) and Google's Gemini multimodal AI.
By shaking your mouse rapidly, a glassmorphic HUD menu appears directly under your cursor. You can then highlight any region on your screen and ask Gemini to write emails, debug code, analyze images, summarize documents, or explain complex layouts.
Shake your cursor rapidly anywhere on the screen to summon the glassmorphic HUD context panel instantly.

Click and drag to select any text or image area on your screen. The border pulses to indicate AI capture.

Get rich, beautifully formatted insights, summaries, or answers rendered directly in the glassmorphic modal.

Configure your Gemini API key and enable launching silently on Windows boot.

- Go to the GitHub Releases Page.
- Download the latest release package:
MagicCursor_v0.0.1_win-x64.zip. - Extract it and run
MagicCursor.exe. (Note: This package is fully self-contained and does not require any installers or runtime installs).
- Coming Soon! We are currently prepping our package manifest to make Magic Cursor available directly via the Microsoft Store for easy installation and automated background updates.
- Windows 10/11
- .NET 10 SDK (or later)
- Visual Studio 2022 (with the .NET Desktop Development workload installed, including Windows App SDK C# Tools)
-
Clone the repository:
git clone https://github.com/muhammadhaseebiqbal-dev/Magic-Cursor.git cd Magic-Cursor
-
Restore dependencies:
dotnet restore
-
Build the project:
dotnet build -c Release -
Publish as a Standalone Portable Package: To generate a zero-dependency self-contained folder that can be distributed anywhere:
dotnet publish -c Release -r win-x64 --self-contained true -p:PublishSingleFile=false -p:WindowsPackageType=None
The compiled executable and required native DLLs will be generated in
bin\Release\net10.0-windows10.0.26100.0\win-x64\publish\.
- 📧 Email & Writing Help: Highlight a rough draft on your screen and ask: "rewrite this email professionally" or "translate this message to Japanese".
- 🖼 Multimodal Image Analysis: Drag-select any image, diagram, chart, or logo on your screen and ask: "what color is this button?", "explain this graph", or "generate HTML code to reproduce this layout". (Image-based queries are automatically routed to Gemini’s vision pipeline).
- 🐞 Developer Debugging: Highlight compilation errors, system logs, or crash tracebacks directly in your IDE or terminal, and ask: "how do I fix this bug?".
- 📝 Fast Screen OCR: Extract text from images, videos, or PDFs where copy-paste is disabled.
We welcome open-source contributions! Whether you want to fix a bug, improve performance, or enhance the design:
- Fork the repository on GitHub.
- Create a feature branch:
git checkout -b feature/amazing-feature. - Commit your changes:
git commit -m "Add some amazing feature". - Push to the branch:
git push origin feature/amazing-feature. - Open a Pull Request for review.
This project is licensed under the MIT License - see the LICENSE file for details.
