CorpusKit Studio

CorpusKit Studio is for people who believe a knowledge base is only as good as the thinking that went into it. Most tools point at a folder, chop it on a blind word count, and hand you a black box. Studio does the opposite. You decide what goes in, where the boundaries fall, and what matters most — so what you build actually holds up when you search it later. Bring your own material — your writing, your research, your licensed or cleared texts — and shape it into a clean, portable, citable corpus that lives entirely on your Mac. WHY CURATION MATTERS Retrieval quality is decided at creation time. Text split mid-argument buries the point; boundaries set with care keep it intact. Studio gives you that editorial control, then does the mechanical work — embedding, indexing, citation — around your judgment. WHAT YOU CAN DO - Import PDF, EPUB with full control over what's extracted - Chunk on natural paragraph boundaries — never mid-sentence, never mid-idea - Weight every section: exclude noise, elevate what matters most - Preserve clean source attribution for trustworthy citations - Export a signed, versioned .corpus bundle to open in CorpusKit Reader WHO IT'S FOR Researchers with their own archives. Authors with a body of work. Coaches and practitioners with their own methods and materials. Anyone curating a collection they hold the rights to and want to get right. PRIVATE BY DESIGN Everything happens on your device. Your material never leaves it. No account, no subscription, no cloud processing.