Extract text and metadata from a wide range of file formats (75+), generate embeddings and post-process at native speeds without needing a GPU.
Key Features
Extensible architecture – Plugin system for custom OCR backends, validators, post-processors, and document extractors
Polyglot – Native bindings for Rust, Python, TypeScript/Node.js, Ruby, Go, Java, C#, PHP, and Elixir
75+ file formats – PDF, Office documents, images, HTML, XML, emails, archives, academic formats across 8 categories
OCR support – Tesseract (all bindings), PaddleOCR (all native bindings), EasyOCR (Python), extensible via plugin API
High performance – Rust core with native PDFium, SIMD optimizations and full parallelism
Flexible deployment – Use as library, CLI tool, REST API server, or MCP server
Memory efficient – Streaming parsers for multi-GB files
Complete Documentation | Installation Guides
Installation
Each language binding provides comprehensive documentation with examples and best practices. Choose your platform to get started:
Key Features
OCR with Table Extraction
Batch Processing
Password-Protected PDFs
Language Detection
Metadata Extraction
AI Coding Assistants
Kreuzberg ships with an Agent Skill that teaches AI coding assistants how to use the library correctly. It works with Claude Code, Codex, Gemini CLI, Cursor, VS Code, Amp, Goose, Roo Code, and any tool supporting the Agent Skills standard.
Documentation: https://docs.kreuzberg.dev/
Contributing
Contributions are welcome! https://github.com/kreuzberg-dev/kreuzberg
License
MIT License - see LICENSE for details. You can use Kreuzberg freely in both commercial and closed-source products with no obligations, no viral effects, and no licensing restrictions.
