Kreuzberg

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

What and Why?

Kreuzberg is a document-intelligence framework with a Rust core and native bindings for 16 languages. It turns documents, images, audio, and source code into clean, structured text — extracting tables, metadata, transcripts, and code intelligence from 96 file formats and 306 programming languages.

Modern AI and RAG pipelines need fast, reliable extraction without a GPU or a stack of heavyweight dependencies. Kreuzberg delivers that from a single Rust core: SIMD-accelerated parsing, pure-Rust PDF, streaming for multi-GB files, and consistent output across every binding. Run it as a library, CLI, REST API, or MCP server.

OCR (Tesseract, PaddleOCR, EasyOCR, and VLM across 143 vision providers), Whisper audio/video transcription, chunking, language detection, embeddings, and structured LLM extraction are all built in.

Features

Supported Formats

96 file formats across 8 categories — Office documents, images (OCR-enabled), web and structured data, email, archives, academic, and audio/video — plus code intelligence for 306 programming languages. See the format reference for the complete list.

⭐ Star this repo to show your support — it helps others discover Kreuzberg.

Quick Start

Language Packages

pip install kreuzberg

uv add kreuzberg

npm install @kreuzberg/node

cargo add kreuzberg

go get github.com/kreuzberg-dev/kreuzberg/v5

dotnet add package Kreuzberg

gem install kreuzberg

composer require kreuzberg-dev/kreuzberg

npm install @kreuzberg/wasm

dart pub add kreuzberg

brew install kreuzberg-dev/tap/kreuzberg

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

# Prebuilt (Homebrew / install.sh / Docker) — MCP is included
brew install kreuzberg-dev/tap/kreuzberg
kreuzberg mcp                                   # stdio (default)

# From source — enable the mcp feature
cargo install kreuzberg-cli --features mcp
kreuzberg mcp

# HTTP transport instead of stdio
kreuzberg mcp --transport http --host 127.0.0.1 --port 8001

{
  "mcpServers": {
    "kreuzberg": { "command": "kreuzberg", "args": ["mcp"] }
  }
}

AI Coding Assistants

Install the Kreuzberg plugin from the kreuzberg-dev/plugins marketplace. It ships the Kreuzberg agent skills (extraction APIs, OCR backends, configuration, language conventions) and works with every major coding agent — expand your harness below.

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

/plugins add https://github.com/kreuzberg-dev/plugins

gemini extensions install https://github.com/kreuzberg-dev/plugins

droid plugin marketplace add https://github.com/kreuzberg-dev/plugins
droid plugin install kreuzberg@kreuzberg

copilot plugin marketplace add https://github.com/kreuzberg-dev/plugins
copilot plugin install kreuzberg@kreuzberg

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["@kreuzberg/opencode-kreuzberg"]
}

Documentation

Full guides, API references for every binding, and the complete format and configuration reference live at kreuzberg.dev. Try it in the browser with the live demo.

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

Join our Discord community for questions and discussion.

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 every per-language binding across the 5 polyglot repos.

License

Elastic License 2.0 (ELv2) — see LICENSE for details. See the Elastic License for the full text.