Raw capture — raw/kreuzberg.md

url: https://github.com/kreuzberg-dev/kreuzberg date_fetched: 2026-07-05 backfilled: true

One Rust engine — 96 file formats, 306 programming languages, native bindings for 15 languages, dual model runtimes, 6 output formats, OCR from any backend, embeddings, structured LLM extraction, token reduction, and more.

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

Feed documents → get clean text, tables, metadata, transcripts, code intelligence · Run it library, CLI, REST API, or MCP server · No GPU needed · Stream multi-GB files · Cache results.

Documents · Images · Spreadsheets · Email · Archives · Code · Audio · Video

Quick start · What you get · Capabilities · CLI · Docs

Feed any document—get structured text. Extract, batch, stream, or crawl.

Xberg is a full content-intelligence engine. One Rust core with fast, accurate extraction from 96 file formats and 306 programming languages. Language bindings for Rust, Python, Node.js, Go, Java, C#, Ruby, PHP, Elixir, Dart, Swift, Zig, WASM, Kotlin, and C FFI. Use it as a library, CLI tool, REST API, or MCP server.

The CLI: 12 commands for extraction, caching, serving, and MCP.

OCR with confidence scores and bounding boxes. Switch backends without code changes.

Web crawl: fetch a page, follow links, extract all documents recursively.

MCP server: AI agents extract documents, detect formats, warm models, manage cache.

REST API: stream large files, get JSON or Markdown, one endpoint for all formats.

Java

Available on Maven Central as io.xberg:xberg. See Java README for the dependency snippet.

Elixir

Add {:xberg, "~> 1.0"} to your mix.exs dependencies. See Elixir README for full documentation.

Kotlin (Android)

Available on Maven Central as io.xberg:xberg-android. See Kotlin README for the dependency snippet.

Swift

Add via Swift Package Manager. See Swift README for full documentation.

Zig

Add via zig fetch. See Zig README for full documentation.

C/C++ (FFI)

Build from source as part of this workspace. See C (FFI) README for full documentation.

CLI Tool

brew install xberg-io/tap/xberg12 commands: extract, batch, detect, formats, version, cache (stats/clear/manifest/warm), serve, mcp, api, embed, chunk, completions.

See CLI usage guide for detailed documentation.

Docker

docker pull ghcr.io/xberg-io/xberg:latestRun in API, CLI, or MCP modes. See Docker guide for examples.

REST API Server

xberg serve --host 0.0.0.0 --port 8000One POST endpoint handles all formats. Returns JSON or Markdown. Stream large files. See API server guide.

MCP Server

xberg mcp --transport stdio9 tools (extract, extract_batch, detect_mime_type, cache_stats, list_formats, cache_clear, get_version, cache_manifest, cache_warm). 3 prompts (extract_document, extract_with_ocr, semantic_search). 4 resources (formats, models, OCR languages, embedding presets).

Add to Claude Desktop or Cursor:

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

Install the Xberg plugin from xberg-io/plugins. Ships extraction APIs, OCR backends, configuration, and language conventions.

Claude Code

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

Codex CLI

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

Search for xberg and select Install Plugin.

Cursor

Settings → Plugins → Add from URL → https://github.com/xberg-io/plugins, then select xberg.

Gemini CLI

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

Factory Droid

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

GitHub Copilot CLI

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

opencode

Add to opencode.json:

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

Extract text from a document:

use xberg::{extract, ExtractInput, ExtractionConfig};
#[tokio::main]
async fn main() -> xberg::Result<()> {
    let config = ExtractionConfig::default();
    let output = extract(
        ExtractInput::from_uri("document.pdf"),
        &config
    ).await?;
    println!("{}", output.results[0].content);
    Ok(())
}

Common use cases — see Quick start guide for language-specific examples, OCR, batch processing, and API configuration.

Full feature list

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

Extract structure from 306 programming languages via tree-sitter:

Powered by tree-sitter-language-pack.

• Tesseract— Native C FFI (Linux/macOS/Windows) and WASM (browser)
• PaddleOCR— ONNX Runtime, mobile-optimized models
• Candle— Pure Rust, CPU-only, lightweight
• VLM— GPT-4 Vision, Claude Vision, Gemini Vision, or 143 providers via liter-llm

Fallback chains. Extensible via plugin system.

Local (ONNX Runtime):

• Preset models: fast, balanced (default), quality, multilingual
• Dimensions: 384, 768, 1024

Provider-hosted:

• OpenAI, Anthropic, Google, Hugging Face, Mistral, Cohere, and 143 providers total
• Via liter-llm integration

Reranking:

• Local ONNX rerankers (cross-encoder models)
• Provider-hosted: Cohere Rerank, others

Local engines: Ollama, LM Studio, vLLM

Remote: OpenAI, Anthropic, Google, Mistral, Cohere, and 143 providers via liter-llm

Schema validation. Temperature, top-p, frequency penalty tuning.

• NER— GLiNER or LLM-based entity recognition
• Redaction— Mask PII (phone, email, SSN, credit card, addresses)
• Summarization— Document and section summaries via LLM
• Translation— Multi-language via LLM
• Page Classification— Tag document pages (cover, toc, content, etc.)
• QR Code Detection— Extract and decode QR codes from images
• Keyword Extraction— YAKE or RAKE algorithms
• Language Detection— Detect document language
• Layout Detection— RT-DETR + TATR models for document structure
• Table Extraction— Cell-level structure and content
• Token Reduction— TOON wire format (~30–50% fewer tokens than JSON)

All 12 commands

Run xberg --help or xberg <command> --help for detailed options.

Full guides, API references for every binding, format reference, and configuration docs live at xberg.io.

• Getting Started
• Quick Start
• Guides
• API Reference
• Format Reference
• Live Demo (browser, WASM)

Contributions are welcome! See CONTRIBUTING.md for guidelines.

Join our Discord community for questions and discussion.

Xberg is one of six open-source projects from Kreuzberg, Inc.:

• Xberg — document intelligence: text, tables, metadata from 91+ formats with optional OCR.
• Xberg Enterprise — managed extraction API with SDKs, dashboards, and observability.
• 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.

MIT License (MIT) — see LICENSE for details.