Skip to main content

Open source

Open tools behind PDF Craft

PDF Craft connects conversion, translation, reading, and knowledge exploration. We publish the libraries behind these workflows.

Projects we maintain

PDF Craft

6,326GitHub starsMIT

An MIT-licensed Python library for recovering text and structure from scanned PDFs and exporting Markdown or EPUB. It supports the PDF conversion workflow available on this site.

EPUB Translator

853GitHub starsMIT

An MIT-licensed Python library for translating EPUB books while keeping the original text available for bilingual reading. It connects to our online EPUB translation experience.

Wiki Graph

385GitHub starsApache 2.0

An Apache 2.0 CLI for building portable .wikg knowledge bases with entities, relationships, evidence, and summaries. PDF Craft desktop also uses Wiki Graph Core for source-aware full-text indexing and search.

Open libraries, distinct products

These repositories are published under their own licenses. The PDF Craft website, hosted service, and client apps have separate terms; the library licenses do not automatically apply to them.