Source: All texts are from Project Gutenberg, a library of free public domain books.
What's included: Works where the US copyright has expired (generally published before 1929 or by authors who died before ~1954). This includes:
What's NOT included: Works still under copyright, such as:
Current corpus: 420 verified books · 66,321 indexed passages · 294 authors
Powered by: YottaDB (high-performance NoSQL database) and FAISS (vector similarity search by Meta AI)
📚 Special thanks to Project Gutenberg for making thousands of public domain books freely available. Their mission to digitize and archive cultural works makes projects like this possible.