LaTeXSnipper is no longer just a "screenshot formula -> LaTeX" utility. It is a desktop workspace built for end-to-end math content workflows:
- Capture and recognize mathematical content from screenshots
- Continue editing and computing in the integrated math workbench
- Handwrite expressions in a dedicated canvas and convert to LaTeX
- Send results back to the main editor or copy to clipboard
The v2.0 Math Workbench supports a complete workflow:
- Capture and recognize formulas from the main window
- Load results into the workbench in one click
- Edit expressions in the
MathLivearea - Use the virtual math keyboard for fractions, superscripts, integrals, series, and more
- Run
Compute / Simplify / Numeric / Expand / Factor / Solve - Write results back to the editor or copy as LaTeX / MathJSON
The v2.3.2 Auto Typesetting Document Window supports source-level editing with synchronized preview:
- Open "Auto Typesetting" from the handwriting window
- Edit full source in the left
TeX Documentpane - Insert complex expressions with the built-in formula editor
- Compile and preview PDF directly
- Navigate bi-directionally between source and PDF via SyncTeX
- Export
.texorPDFwhen needed
The v2.1 handwriting window supports the following flow:
- Open "Handwriting Recognition" from the main window
- Write formulas directly on an isolated canvas
- Trigger MathCraft OCR automatically after pen-up
- See live
LaTeX outputand rendered preview on the right - Copy LaTeX directly or insert it back into the main editor
| Feature | Description |
|---|---|
| 📸 Formula recognition | MathCraft OCR for formulas, text, and mixed content |
| ✍️ Handwriting recognition | Dedicated handwriting window with auto-recognition and live preview |
| 🧮 Math workbench | Separate workspace for editing, computation, and write-back |
| ⌨️ Formula editing | Integrated MathLive math-field with virtual math keyboard |
| 🔄 Multi-format export | LaTeX, Markdown, MathML, HTML, OMML, SVG |
| 📐 Core computation | Compute, simplify, numeric evaluate, expand, factor, solve |
| 🧠 Advanced fallback | Local SymPy/mpmath engine for harder expressions |
| 🌙 Theme support | Light/Dark adaptation across windows and tools |
| 🔐 Offline-first | Recognition and advanced solving can run locally for privacy |
The workbench currently covers common scenarios such as:
- Polynomial expansion
- Factorization
- Equation solving
- Irrational/complex root fallback solving
- Definite and improper integrals
- Infinite series
- Infinite products
- Limits
- Derivatives
- Numeric approximation and constant recognition
For heavy expressions, the engine uses automatic fallback:
- Try frontend
Compute Enginefirst - Switch to local advanced engine on timeout/failure/unreliable results
- Use
SymPy/mpmathfor robust fallback - Recover closed forms for selected known constants from numeric output
- Visit the Releases page
- Download the latest
LaTeXSnipper Final Stable.exe - Run the installer
- Complete environment setup via the dependency wizard on first launch
- Start capturing, handwriting, or using the math workbench
git clone https://github.com/SakuraMathcraft/LaTeXSnipper.git
cd LaTeXSnipper
python -m venv .venv
.\.venv\Scripts\activate
pip install -r requirements.txt
python src/main.pyLaTeXSnipper/
|-- mathcraft_ocr/ # Standalone MathCraft OCR runtime and CLI
|-- src/
| |-- main.py # Main desktop application entry
| |-- deps_bootstrap.py # Dependency wizard and runtime verification
| |-- distribution.py # GitHub / Microsoft Store channel policy
| |-- backend/ # OCR wrapper, CUDA diagnostics, capture, platform services
| |-- core/ # Document composition, export contracts, restart contracts
| |-- editor/ # Math workbench and formula editing UI
| |-- handwriting/ # Handwriting canvas, PDF preview, document tools
| |-- assets/ # Icons and bundled web/math resources
| `-- deps/ # Bundled/local Python dependency environment
|-- Inno/ # GitHub Release installer scripts
|-- packaging/msix/ # Microsoft Store MSIX manifest and notes
|-- scripts/ # Build, release, and regression utilities
|-- docs/ # Design and architecture notes
|-- LaTeXSnipper.spec # PyInstaller GitHub build
|-- LaTeXSnipper.offline.spec # PyInstaller offline-model build
|-- pyproject.toml
|-- requirements.txt
|-- requirements-build.txt
|-- version_info.txt
`-- README.md
Contributions are welcome:
- Fork the repository
- Create a feature branch
- Commit your changes
- Push your branch
- Open a Pull Request
Recommended focus areas:
- Handwriting UX
- Math workbench UX
- Advanced solver stability
- Packaged runtime verification
- Theme consistency across windows
This project is open-sourced under the MIT License.
Special thanks to:
| Download | Issues | Discussions | Wiki |
|---|---|---|---|
| Latest Release | Open an Issue | Discussions | Project Wiki |
