Plain-AyI
← All projects
Developer building blocks

PyG (PyTorch Geometric)

A code library for AI that learns from networks of connected things, like social networks or molecules.

Research-backed

What it does

Some data is best shown as a network, or "graph": dots connected by lines. Examples include friends in a social network, papers that cite each other, or atoms in a molecule. PyG is a library for building AI models, called graph neural networks, that learn from this kind of data.

It's built on PyTorch, a popular AI library, and includes many ready-made models from published research. Its makers say a first model takes only 10 to 20 lines of code, and that it can handle very large graphs.

Who it's for

Researchers and data scientists working with connected data.

Can I use it without coding?

Developers only. It's a Python library for programmers. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it