source{d} builds the open-source components that make machine learning on source code a reality: from datasets to full-fledged demos using our stack, all is freely available in our projects below.

The source{d} engine wraps our retrieval and language analysis pipeline as a single entry point, allowing you to turn millions of code repositories into UASTs ready for machine learning tools & models

Interested in trying a live demo of source{d} engine? Let us know


We still have things to polish here, soon to be released. Join our community to keep posted!


data retrieval tools

language analysis tools

machine learning tools