kreuzberg-dev/kreuzberg

A polyglot document intelligence framework with a Rust core. Extract text, metadata, and structured information from PDFs, Office documents, images, and 76+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

92
/ 100
Verified

Supports pluggable OCR backends (Tesseract, PaddleOCR, EasyOCR) and custom processors via a plugin API, enabling extensible extraction pipelines. Uses native PDFium with SIMD optimizations and streaming parsers to handle multi-GB files efficiently without GPU acceleration. Deployable as a library, CLI, REST API, or Claude MCP server, with precompiled binaries across x86_64/aarch64 on Linux/macOS and full WASM support for browser/edge environments.

6,689 stars and 121,901 monthly downloads. Used by 6 other packages. Actively maintained with 736 commits in the last 30 days. Available on PyPI.

Maintenance 25 / 25
Adoption 25 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

6,689

Forks

316

Language

Rust

License

MIT

Last pushed

Mar 12, 2026

Monthly downloads

121,901

Commits (30d)

736

Reverse dependents

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/kreuzberg-dev/kreuzberg"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.