← Latest products

Kreuzberg

Modern async Python library for document text extraction. The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence. I'm excited to showcase Kreuzberg!

LibraryOpen source

9,495 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. YaraDB

    github.com

    Lightweight open-source document database built with FastAPI

    Hacker News10 pts

  2. DocsRouter

    docsrouter.com

    The OpenRouter for OCR and Vision Models

    Hacker News14 pts

  3. PyAirbyte

    docs.airbyte.com

    We built a lightweight Python library for ELT

    Hacker News18 pts

  4. Codon

    regmedia.co.uk

    A Compiler for High-Performance Pythonic Applications and DSLs [pdf]

    Hacker News54 pts

  5. Open-Source Document Extraction Tool

    github.com

    Open-source spreadsheets platform for deep research and document processing

    Hacker News13 pts