kreuzberg

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ 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.

8,572

499

Kreuzberg

Extract text, metadata, and code intelligence from 96 file formats and 306 programming languages at native speeds without needing a GPU.

Key Features

Code intelligence – Extract functions, classes, imports, symbols, and docstrings from 306 programming languages via tree-sitter. Results in ExtractionResult.code_intelligence with semantic chunking
Extensible architecture – Plugin system for custom OCR backends, validators, post-processors, document extractors, and renderers
Polyglot – Native bindings for Rust, Python, TypeScript/Node.js, Ruby, Go, Java, Kotlin, C#, PHP, Elixir, R, Dart, Swift, Zig, and C
96 file formats – PDF, Office documents, images, HTML, XML, emails, archives, academic formats across 8 categories
LLM intelligence – VLM OCR (GPT-4o, Claude, Gemini, Ollama), structured JSON extraction with schema constraints, and provider-hosted embeddings via 143 LLM providers (including local engines: Ollama, LM Studio, vLLM, llama.cpp) through liter-llm
OCR support – Tesseract (all bindings, including Tesseract-WASM for browsers), PaddleOCR (all native bindings), EasyOCR (Python), VLM OCR (143 vision model providers including local engines), extensible via plugin API
High performance – Rust core with pure-Rust PDF, SIMD optimizations and full parallelism
Flexible deployment – Use as library, CLI tool, REST API server, or MCP server
TOON wire format – Token-efficient serialization for LLM/RAG pipelines, ~30-50% fewer tokens than JSON
GFM-quality output – Comrak-based rendering with proper fenced code blocks, table nodes, bracket escaping, and cross-format parity (Markdown, HTML, Djot, Plain)
HTML passthrough – HTML-to-Markdown conversion uses html-to-markdown output directly, bypassing lossy intermediate round-trips
Memory efficient – Streaming parsers for multi-GB files

Complete Documentation | Live Demo | Installation Guides

Installation

Each language binding provides comprehensive documentation with examples and best practices. Choose your platform to get started:

Scripting Languages:

Python – PyPI package, async/sync APIs, OCR backends (Tesseract, PaddleOCR, EasyOCR)
Ruby – RubyGems package, idiomatic Ruby API, native bindings
PHP – Composer package, modern PHP 8.2+ support, type-safe API, async extraction
Elixir – Hex package, OTP integration, concurrent processing
R – r-universe package, idiomatic R API, extendr bindings
Dart / Flutter – pub.dev package, flutter_rust_bridge runtime, native bindings for macOS/iOS/Android/Linux/Windows

JavaScript/TypeScript:

@kreuzberg/node – Native NAPI-RS bindings for Node.js/Bun, fastest performance
@kreuzberg/wasm – WebAssembly for browsers/Deno/Cloudflare Workers, comprehensive format and OCR support (PDF, Excel, archives, all office formats, real Tesseract via the WASI build) — only ORT-dependent features (paddle-ocr, layout detection, embeddings, auto-rotate) and server modes (api/mcp/cli) are excluded

Compiled Languages:

Go – Go module with FFI bindings, context-aware async
Java – Maven Central, Foreign Function & Memory API
Kotlin – Maven Central, Kotlin/JVM with idiomatic data classes, sealed enums, and coroutine-based async
C# – NuGet package, .NET 6.0+, full async/await support
Swift – Swift Package Manager, macOS 13+/iOS 16+, native Swift types and async/await

Native:

Rust – Core library, flexible feature flags, zero-copy APIs
Zig – zig fetch + build.zig.zon, idiomatic error sets, optional types, slice-based memory
C (FFI) – C header + shared library, pkg-config/CMake support, cross-platform

Containers:

Docker – Official images with API, CLI, and MCP server modes (Core: ~1.0-1.3GB, Full: ~1.0-1.3GB with OCR + legacy format support)

Command-Line:

CLI – Cross-platform binary, batch processing, MCP server mode

All language bindings include precompiled binaries for both x86_64 and aarch64 architectures on Linux and macOS.

Platform Support

Complete architecture coverage across all language bindings:

Language	Linux x86_64	Linux aarch64	macOS ARM64	Windows x64
Python	✅	✅	✅	✅
Node.js	✅	✅	✅	✅
WASM	✅	✅	✅	✅
Ruby	✅	✅	✅	-
R	✅	✅	✅	✅
Elixir	✅	✅	✅	✅
Go	✅	✅	✅	✅
Java	✅	✅	✅	✅
Kotlin	✅	✅	✅	✅
C#	✅	✅	✅	✅
PHP	✅	✅	✅	✅
Swift	-	-	✅	-
Dart	✅	✅	✅	✅
Zig	✅	✅	✅	✅
Rust	✅	✅	✅	✅
C (FFI)	✅	✅	✅	✅
CLI	✅	✅	✅	✅
Docker	✅	✅	✅	-

Note: ✅ = Precompiled binaries available with instant installation. WASM runs in any environment with WebAssembly support (browsers, Deno, Bun, Cloudflare Workers). All platforms are tested in CI. MacOS support is Apple Silicon only.

Mobile (iOS, Android)

Target	ORT-dependent features*
iOS (`aarch64-apple-ios`, `aarch64-apple-ios-sim`)	✅
Android arm64 (`aarch64-linux-android`)	✅
Android x86_64 emulator (`x86_64-linux-android`)	❌

*ORT-dependent features: PaddleOCR, layout detection, embeddings, auto-rotate.
All non-ORT capabilities (Tesseract OCR, every document format, chunking, language detection, keywords, tree-sitter code intelligence, API/MCP, LLM) are available on all four mobile targets.

The x86_64-linux-android emulator triple lacks an ORT prebuilt upstream; kreuzberg's kreuzberg crate exposes an android-target aggregate feature that selects the same no-ORT feature set as WASM. The kreuzberg-ffi and kreuzberg-dart crates auto-select that aggregate for the emulator via target-conditional dependencies — host and arm64 phones get full features automatically.

Browsers / Edge (WebAssembly)

WASM excludes the same ORT-dependent feature set as the Android x86_64 emulator. The shared no-ORT base lives behind the no-ort-target feature in the core crate; both wasm-target and android-target compose it.

Embeddings Support (Optional)

To use embeddings functionality:

Install ONNX Runtime 1.24+:
- Linux: Download from ONNX Runtime releases (Debian packages may have older versions)
- MacOS: brew install onnxruntime
- Windows: Download from ONNX Runtime releases
Use embeddings in your code - see Embeddings Guide

Note: Kreuzberg requires ONNX Runtime version 1.24+ for embeddings. All other Kreuzberg features work without ONNX Runtime.

Supported Formats

96 file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.

Office Documents

Category	Formats	Capabilities
Word Processing	`.docx`, `.docm`, `.dotx`, `.dotm`, `.dot`, `.odt`, `.pages`	Full text, tables, lists, images, metadata, styles
Spreadsheets	`.xlsx`, `.xlsm`, `.xlsb`, `.xls`, `.xla`, `.xlam`, `.xltm`, `.xltx`, `.xlt`, `.ods`, `.numbers`	Sheet data, formulas, cell metadata, charts
Presentations	`.pptx`, `.pptm`, `.ppsx`, `.potx`, `.potm`, `.pot`, `.key`	Slides, speaker notes, images, metadata
PDF	`.pdf`	Text, tables, images, metadata, OCR support
eBooks	`.epub`, `.fb2`	Chapters, metadata, embedded resources
Database	`.dbf`	Table data extraction, field type support
Hangul	`.hwp`, `.hwpx`	Korean document format, text extraction

Images (OCR-Enabled)

Category	Formats	Features
Raster	`.png`, `.jpg`, `.jpeg`, `.gif`, `.webp`, `.bmp`, `.tiff`, `.tif`	OCR, table detection, EXIF metadata, dimensions, color space
Advanced	`.jp2`, `.jpx`, `.jpm`, `.mj2`, `.jbig2`, `.jb2`, `.pnm`, `.pbm`, `.pgm`, `.ppm`	Pure Rust decoders (JPEG 2000, JBIG2), OCR, table detection
Vector	`.svg`	DOM parsing, embedded text, graphics metadata

Web & Data

Category	Formats	Features
Markup	`.html`, `.htm`, `.xhtml`, `.xml`, `.svg`	DOM parsing, metadata (Open Graph, Twitter Card), link extraction
Structured Data	`.json`, `.yaml`, `.yml`, `.toml`, `.csv`, `.tsv`	Schema detection, nested structures, validation
Text & Markdown	`.txt`, `.md`, `.markdown`, `.djot`, `.mdx`, `.rst`, `.org`, `.rtf`	CommonMark, GFM, Djot, MDX, reStructuredText, Org Mode, Rich Text

Email & Archives

Category	Formats	Features
Email	`.eml`, `.msg`	Headers, body (HTML/plain), attachments, UTF-16 support
Archives	`.zip`, `.tar`, `.tgz`, `.gz`, `.7z`	Recursive extraction, nested archives, metadata

Academic & Scientific

Category	Formats	Features
Citations	`.bib`, `.ris`, `.nbib`, `.enw`, `.csl`	BibTeX/BibLaTeX, RIS, PubMed/MEDLINE, EndNote XML, CSL JSON
Scientific	`.tex`, `.latex`, `.typ`, `.typst`, `.jats`, `.ipynb`	LaTeX, Typst, JATS journal articles, Jupyter notebooks
Publishing	`.fb2`, `.docbook`, `.dbk`, `.opml`	FictionBook, DocBook XML, OPML outlines
Documentation	`.pod`, `.mdoc`, `.troff`	Perl POD, man pages, troff

Complete Format Reference →

Code Intelligence (300+ Languages)

Feature	Description
Structure Extraction	Functions, classes, methods, structs, interfaces, enums
Import/Export Analysis	Module dependencies, re-exports, wildcard imports
Symbol Extraction	Variables, constants, type aliases, properties
Docstring Parsing	Google, NumPy, Sphinx, JSDoc, RustDoc, and 10+ formats
Diagnostics	Parse errors with line/column positions
Syntax-Aware Chunking	Split code by semantic boundaries, not arbitrary byte offsets

Key Features

<details> <summary><strong>OCR with Table Extraction</strong></summary>

Multiple OCR backends (Tesseract, EasyOCR, PaddleOCR) with intelligent table detection and reconstruction. Extract structured data from scanned documents and images with configurable accuracy thresholds.

OCR Backend Documentation →

</details> <details> <summary><strong>Batch Processing</strong></summary>

Process multiple documents concurrently with configurable parallelism. Optimize throughput for large-scale document processing workloads with automatic resource management.

Batch Processing Guide →

</details> <details> <summary><strong>Password-Protected PDFs</strong></summary>

Handle encrypted PDFs with single or multiple password attempts. Supports both RC4 and AES encryption with automatic fallback strategies.

PDF Configuration →

</details> <details> <summary><strong>Language Detection</strong></summary>

Automatic language detection in extracted text using fast-langdetect. Configure confidence thresholds and access per-language statistics.

Language Detection Guide →

</details> <details> <summary><strong>Metadata Extraction</strong></summary>

Extract comprehensive metadata from all supported formats: authors, titles, creation dates, page counts, EXIF data, and format-specific properties.

Metadata Guide →

</details>

AI Coding Assistants

Install the Kreuzberg plugin from the kreuzberg-dev/plugins marketplace:

/plugin marketplace add kreuzberg-dev/plugins
/plugin install kreuzberg@kreuzberg

Works with Claude Code, Codex, Cursor, Gemini CLI, Factory Droid, GitHub Copilot CLI, and opencode. See the marketplace README for harness-specific install instructions.

The plugin ships the Kreuzberg agent skill — previously distributed from the in-tree skills/ directory — and teaches assistants the extraction APIs, configuration fields, OCR backends, and language-specific conventions.

Documentation

Installation Guide – Setup and dependencies
User Guide – Comprehensive usage guide
API Reference – Complete API documentation
Format Support – Supported file formats
OCR Backends – OCR engine setup
CLI Guide – Command-line usage
Migration Guides – Upgrading from other libraries

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

Part of Kreuzberg.dev

Kreuzberg Cloud — managed extraction API with SDKs, dashboards, and observability.
kreuzcrawl — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
html-to-markdown — fast, lossless HTML→Markdown engine.
liter-llm — universal LLM API client with native bindings for 14 languages and 143 providers.
tree-sitter-language-pack — tree-sitter grammars and code-intelligence primitives.
alef — the polyglot binding generator that produces all per-language bindings.
Discord — community, roadmap, announcements.

License

Elastic License 2.0 (ELv2) - see LICENSE for details. See https://www.elastic.co/licensing/elastic-license for the full license text.

FAQ

What is Kreuzberg?

Kreuzberg is a polyglot document intelligence framework with a Rust core. It extracts text, metadata, and code intelligence from 96 file formats and 306 programming languages at native speeds without needing a GPU. It provides native bindings for Rust, Python, TypeScript/Node.js, Ruby, Go, Java, Kotlin, C#, PHP, Elixir, R, Dart, Swift, Zig, and C.

How does Kreuzberg differ from other document extraction tools?

Kreuzberg: Rust core, 96 formats, 306 languages, polyglot bindings, code intelligence via tree-sitter, VLM OCR, native speeds, no GPU needed
Apache Tika: Java-based, broader format support, but slower, no code intelligence, no VLM OCR
pdfplumber: Python-only, PDF focus, slower, no code intelligence
unstructured: Python-based, good format coverage, but slower, requires more dependencies

Kreuzberg's Rust core with SIMD optimizations and parallelism delivers 10-100x faster extraction than Python alternatives.

What are Kreuzberg's key features?

Code intelligence — Extract functions, classes, imports, symbols, docstrings from 306 languages via tree-sitter
Extensible architecture — Plugin system for custom OCR backends, validators, post-processors, document extractors, renderers
Polyglot bindings — Native bindings for 14+ languages (Rust, Python, Node.js, Ruby, Go, Java, Kotlin, C#, PHP, Elixir, R, Dart, Swift, Zig, C)
96 file formats — PDF, Office documents, images, HTML, XML, emails, archives, academic formats across 8 categories
LLM intelligence — VLM OCR (GPT-4o, Claude, Gemini, Ollama), structured JSON extraction, embeddings via 143 LLM providers
OCR support — Tesseract (all bindings including WASM for browsers), PaddleOCR, EasyOCR, VLM OCR, extensible via plugin API
High performance — Rust core with pure-Rust PDF, SIMD optimizations, full parallelism
Flexible deployment — Library, CLI tool, REST API server, or MCP server
TOON wire format — Token-efficient serialization for LLM/RAG pipelines, ~30-50% fewer tokens than JSON
GFM-quality output — Comrak-based Markdown rendering with proper fenced code blocks, table nodes
Memory efficient — Streaming parsers for multi-GB files

What file formats does Kreuzberg support?

8 categories covering 96 formats:

Documents — PDF, DOCX, DOC, ODT, RTF, Hangul
Office — XLSX, XLS, PPTX, PPT, ODS, iWork
Images — PNG, JPEG, TIFF, BMP, GIF, WebP
Web — HTML, XML, XHTML, SVG
Emails — MSG, EML, PST
Archives — ZIP, TAR, GZ, TGZ, 7Z
Academic — LaTeX, BibTeX, RIS
Code — 306 programming languages via tree-sitter

How do I get started?

Choose your platform:

Python:

pip install kreuzberg

See Python docs

Node.js:

npm install @kreuzberg/node

See Node.js docs

Rust:

cargo add kreuzberg

See Rust docs

Docker:

docker pull ghcr.io/kreuzberg-dev/kreuzberg:latest

See Docker docs

What LLM/VLM providers are supported?

143 providers including:

OpenAI — GPT-4o (vision), text models
Anthropic — Claude (vision), Claude 3.5 Sonnet
Google — Gemini (vision), Gemini 2.0 Flash
Local engines — Ollama, LM Studio, vLLM, llama.cpp
Cloud providers — Fireworks, Together, Groq, OpenRouter
All OpenAI-compatible endpoints

What OCR backends are available?

Tesseract — All bindings, including Tesseract-WASM for browsers
PaddleOCR — All native bindings (Python, Node.js, etc.)
EasyOCR — Python binding
VLM OCR — 143 vision model providers (GPT-4o, Claude, Gemini, Ollama local)
Custom OCR — Extensible via plugin API

What is the TOON wire format?

TOON is Kreuzberg's token-efficient serialization format for LLM/RAG pipelines. It uses ~30-50% fewer tokens than JSON, making it ideal for:

Large document processing
RAG system integration
LLM context window optimization
Cost reduction in API calls

What is code intelligence extraction?

Kreuzberg extracts semantic code information via tree-sitter:

Functions — Names, parameters, return types, docstrings
Classes — Names, methods, inheritance, properties
Imports — Module names, import paths
Symbols — Variables, constants, type definitions
Docstrings — Documentation comments

Results in ExtractionResult.code_intelligence with semantic chunking.

Does Kreuzberg work in browsers?

Yes! The WASM package (@kreuzberg/wasm) supports browsers, Deno, and Cloudflare Workers with:

PDF, Excel, archives, all office formats
Real Tesseract OCR via WASI build
Only ORT-dependent features excluded (PaddleOCR, layout detection, embeddings, auto-rotate)

What deployment options are available?

Library — Use as a dependency in your application
CLI — Cross-platform binary for batch processing
REST API server — HTTP endpoint for document extraction
MCP server — Model Context Protocol server for AI assistants
Docker — Official images with API, CLI, and MCP modes

What languages have native bindings?

Language	Package Manager	Status
Rust	Cargo	✅ Core library
Python	PyPI	✅ Full support
Node.js	npm (NAPI-RS)	✅ Fastest performance
WASM	npm	✅ Browser/Deno/CF Workers
Ruby	RubyGems	✅ Native bindings
Go	Go modules	✅ FFI bindings
Java	Maven Central	✅ Foreign Function API
Kotlin	Maven Central	✅ Coroutine-based
C#	NuGet	✅ .NET 6.0+
PHP	Composer	✅ PHP 8.2+
Elixir	Hex	✅ OTP integration
R	r-universe	✅ extendr bindings
Dart/Flutter	pub.dev	✅ flutter_rust_bridge
Swift	SPM	✅ macOS 13+/iOS 16+
Zig	build.zig.zon	✅ Idiomatic API
C (FFI)	pkg-config/CMake	✅ Header + shared lib

What platforms are supported?

All bindings support:

Linux — x86_64 and aarch64
macOS — ARM64
Windows — x64 (most bindings)

Precompiled binaries included for all architectures.

What license does Kreuzberg use?

Elastic-2.0 License — open-source with commercial use restrictions. See LICENSE for details.

Where can I get help?

Documentation: docs.kreuzberg.dev
Live Demo: docs.kreuzberg.dev/demo.html
Discord: discord.gg/xt9WY3GnKR
Hugging Face: huggingface.co/Kreuzberg
GitHub Issues: github.com/kreuzberg-dev/kreuzberg/issues

Repository

kreuzberg-dev

kreuzberg-dev/kreuzberg

Created

January 31, 2025

Updated

June 15, 2026

Language

Rust

kreuzberg

Kreuzberg

Key Features

Installation

Platform Support

Mobile (iOS, Android)

Browsers / Edge (WebAssembly)

Embeddings Support (Optional)

Supported Formats

Office Documents

Images (OCR-Enabled)

Web & Data

Email & Archives

Academic & Scientific

Code Intelligence (300+ Languages)

Key Features

AI Coding Assistants

Documentation

Contributing

Part of Kreuzberg.dev

License

FAQ

What is Kreuzberg?

How does Kreuzberg differ from other document extraction tools?

What are Kreuzberg's key features?

What file formats does Kreuzberg support?

How do I get started?

What LLM/VLM providers are supported?

What OCR backends are available?

What is the TOON wire format?

What is code intelligence extraction?

Does Kreuzberg work in browsers?

What deployment options are available?

What languages have native bindings?

What platforms are supported?

What license does Kreuzberg use?

Where can I get help?

Repository

Created

Updated

Language

Category