kreuzberg

kreuzberg

Multilingual document intelligence framework that extracts text, metadata, and more from over 97 formats.

MCPDataOpen source
Type
MCP
Transport
http
Open source
Yes
GitHub Stars
★ 8.5k
Source
mcp-github

Overview

Kreuzberg is a multilingual document intelligence framework built on a Rust core, capable of extracting text, metadata, images, and structured information from 97+ formats including PDFs, Office documents, and images. It supports bindings for multiple programming languages such as Rust, Python, and Node.js, and can be used via CLI, REST API, or MCP server. Ideal for AI and RAG pipelines requiring fast and reliable document content extraction.

Capabilities

  • Extract text from 97+ formats
  • Extract metadata and images
  • Support for 306 programming languages
  • Built-in OCR and audio transcription
  • SIMD-accelerated parsing
  • Streaming processing of large files

Use cases

Document content extractionAI and RAG pipelinesCode intelligence extractionMultimedia file processing

Setup

Requires: API Key
Install via npm: `npm install @kreuzberg/node` or use the package manager corresponding to your language.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

What file formats does Kreuzberg support?

PDF, Office documents, images, and over 97 other formats.

Does Kreuzberg support OCR?

Yes, it includes built-in OCR engines such as Tesseract and PaddleOCR.

Related skills