Open Textbook Library
The Open Textbook Library is a curated catalogue of free, openly licensed textbooks, run by the University of Minnesota's Center for Open Education. Instead of lesson fragments, it lists complete, book-length texts across the common college subjects: economics, biology, psychology, mathematics, computer science, business, and many more. Its distinguishing feature is the review layer: most entries carry peer reviews written by faculty, so you can gauge a book's quality and accuracy before you commit to it.
Each catalogue entry links out to the full text, usually a PDF and often HTML or other formats hosted by the original publisher or platform. There is no single bulk download of every book, so assembling a corpus means working through the catalogue and fetching titles one by one, respecting each book's own source. Full textbooks are long, so for RAG you will want to split them into sections or sub-chapters, keeping the headings as context, so a retriever can surface the specific passage that answers a question rather than a whole chapter.
It is a strong fit for tutoring assistants, study tools, and any education system that gains from authoritative, structured explanations at higher-education level. Because the texts are written as teaching material, they define terms and build concepts in order, which grounds a model more cleanly than scattered web pages.
Licensing needs care. Titles carry a range of Creative Commons licences and the exact terms vary from book to book, so whether you can use one commercially, must attribute it, or must share adaptations alike depends on the individual title. Treat commercial use as unclear across the catalogue and check each book before building on it. The collection is curated rather than exhaustive, so read it as a quality-first selection, not a complete library.
Alongside it, LibreTexts offers a larger, more interconnected collection (though often under non-commercial terms), and OER Commons casts a wider net across formats. The Open Textbook Library is where to start when you want vetted, whole-book material you can trust.
Related sources
CASE Network (1EdTech)
A public registry of machine-readable learning-standard frameworks from all 50 US states and other issuing agencies, run by 1EdTech in the CASE JSON format. The digitally referenceable spine of what to teach, at which level and in what order, rather than the teaching content itself.
CK-12 Foundation
Free K-12 library of customisable FlexBook textbooks, strong in maths and science, with adaptive practice, interactive simulations and study guides, organised by grade level and aligned to state standards. Non-commercial licence.
Common Core State Standards
The US Common Core State Standards for English language arts and mathematics, defined grade by grade from kindergarten to grade twelve. A widely adopted curriculum framework, available in machine-readable form through ASN and CASE.
Khan Academy
A free nonprofit learning platform organised as a subject-to-skill knowledge tree across maths, science, economics and the humanities, from primary through early college. Videos, articles and mastery-based exercises, but non-commercial licensing and no public data API.