Corpus
Structured research engine. Absurdly fast. Open source.
3 followers
Structured research engine. Absurdly fast. Open source.
3 followers
Document research shouldn't cost five figures. Corpus is an open-source research engine that turns mountains of documents into structured answers. Upload hundreds of files, ask dozens of questions, get back a clean spreadsheet—in parallel across your entire corpus. No more reading PDFs one by one or copy-pasting into chatbots. Upload, query, extract. Built this solo because I needed a better way. AGPL licensed, open codebase. Contributors welcome.
Free Options
Launch Team / Built With
Render: Get up to $100K in startup creditsThe fastest way to launch and scale your startup in the cloud
Promoted
Hey Product Hunt! Corpus is an open-source document research engine.
Upload a stack of documents, define your questions, and get a structured spreadsheet of answers extracted in parallel across everything. SQL for unstructured data.
Works on PDFs, Word docs, text files, audio transcripts. Built for research, due diligence, contract review, or anywhere you need the same answers from a lot of documents.
AGPL licensed, built to be extended.