Skills
.Work. You
Rest

kreuzberg

Official

Extract text, tables, and images from 75+ formats

Software Engineering#ocr#embeddings#bindings#multi-format#language-detection#document-extraction
Authorkreuzberg-dev
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Kreuzberg is a high-performance document intelligence library that enables programmatic extraction of text, tables, metadata, and images from 75+ formats across PDFs, Office documents, images (with OCR), HTML, email, archives, and academic formats.

Core Features & Use Cases

  • Efficient multi-format extraction: pull text, tables, and metadata from diverse document types for indexing, search, and downstream processing.
  • OCR-enabled data capture: automatically recognize text in scanned images and image-based PDFs via configurable backends.
  • Batch processing and extension points: process multiple files, with plugin support for post-processors, validators, and OCR backends.

Quick Start

Process a sample document to extract structured content and inspect results.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: kreuzberg
Download link: https://github.com/kreuzberg-dev/kreuzberg/archive/main.zip#kreuzberg

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.