majcheradam/ocrbase

📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable.

99 best points · 36 comments · 1 Hacker News post · 29 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API (99 points, 36 comments, by adammajcher, 2026-01-20)