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.
Overview
kreuzberg-dev/kreuzberg is a Rust MCP server licensed under MIT. 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. Topics: text-extraction, document-intelligence, metadata-extraction, pdf-extraction, pdfium, python, rag, table-extraction, tesseract, ffi, golang, java, node, ruby, rust, wasm, elixir, php, bun, csharp.
Ranked #10 out of 25632 indexed tools.
In the top 1% of all indexed tools.
Has 6,698 GitHub stars.
Used by 40 other projects.
Has 26 contributors.
Actively maintained with commits in the last week.
Ecosystem
Signal Breakdown
Matched Queries
From the README
# Kreuzberg
<div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
<a href="https://crates.io/crates/kreuzberg">
</a>
<a href="https://hex.pm/packages/kreuzberg">
</a>
<a href="https://pypi.org/project/kreuzberg/">
</a>
<a href="https://www.npmjs.com/package/@kreuzberg/node">
</a>
<a href="https://www.npmjs.com/package/@kreuzberg/wasm">
</a>
<a href="https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg">
</a>
<a href="https://github.com/kreuzberg-dev/kreuzberg/releases">
</a>
<a href="https://www.nuget.org/packages/Kreuzberg/">
</a>
<a href="https://packagist.org/packages/kreuzberg/kreuzberg">
</a>
<a href="https://rubygems.org/gems/kreuzberg">
</a>
<a href="https://kreuzberg-dev.r-universe.dev/kreuzberg">
</a>
<a href="https://github.com/kreuzberg-dev/kreuzberg/pkgs/container/kreuzberg">
</a>
<a href="https Read full README on GitHub →