Xberg

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

Xberg is the next iteration of Kreuzberg. Same document-intelligence engine, rebuilt and rebranded under a fresh v1 line.

What and Why?

Xberg 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. Xberg 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 Xberg.

Quick Start

Language Packages

pip install xberg

uv add xberg

npm install @xberg-io/xberg

cargo add xberg

go get github.com/xberg-io/xberg

dotnet add package Xberg

gem install xberg

composer require xberg-io/xberg

npm install @xberg-io/xberg-wasm

dart pub add xberg

brew install xberg-io/tap/xberg

docker pull ghcr.io/xberg-io/xberg:latest

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

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

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

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

AI Coding Assistants

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

/plugin marketplace add xberg-io/plugins
/plugin install xberg@xberg

/plugins add https://github.com/xberg-io/plugins

gemini extensions install https://github.com/xberg-io/plugins

droid plugin marketplace add https://github.com/xberg-io/plugins
droid plugin install xberg@xberg

copilot plugin marketplace add https://github.com/xberg-io/plugins
copilot plugin install xberg@xberg

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

Documentation

Full guides, API references for every binding, and the complete format and configuration reference live at xberg.io. 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 Xberg.dev

• crawlberg — 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

MIT License (MIT) — see LICENSE for details. See the MIT License for the full text.