What this is: A tool that runs entirely on your computer (no internet required after setup) to extract text from scanned PDFs and images with high accuracy.
You need Python 3.12 or newer installed. This is the only manual step.
Check if you already have it:
If you see Python 3.12.x or higher, you're good. Skip to the next section.
If Python is missing or too old:
Go to python.org/downloads
Click the yellow "Download Python 3.x.x" button

Run the installer
<aside> ⚠️
Windows only — important: On the first screen of the installer, check the box that says "Add Python to PATH" before clicking Install. If you skip this, the tool won’t be able to find Python and will fail to launch

</aside>
Download and unzip the GLM-OCR folder to wherever you'd like to keep it (e.g. your Desktop or Documents)

Open the folder
macOS: