Skip to content

AI Coding Assistants

The Kreuzberg plugin teaches AI coding assistants how to use the library — covering extraction, configuration, OCR, chunking, embeddings, batch processing, error handling, and plugins across Python, Node.js/TypeScript, Rust, and CLI.

Installing

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.

Claude Code 
/plugin marketplace add kreuzberg-dev/plugins
/plugin install kreuzberg@kreuzberg
Codex CLI 
/plugins add https://github.com/kreuzberg-dev/plugins
Then search for `kreuzberg` and select **Install Plugin**.
Cursor Settings → Plugins → Add from URL → `https://github.com/kreuzberg-dev/plugins`, then select **Kreuzberg**.
Gemini CLI 
gemini extensions install https://github.com/kreuzberg-dev/plugins
Factory Droid 
droid plugin marketplace add https://github.com/kreuzberg-dev/plugins
droid plugin install kreuzberg@kreuzberg
GitHub Copilot CLI 
copilot plugin marketplace add https://github.com/kreuzberg-dev/plugins
copilot plugin install kreuzberg@kreuzberg
opencode Add the package to `opencode.json`: 
{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["@kreuzberg/opencode-kreuzberg"]
}

What the Skill Provides

When your AI coding assistant discovers the skill, it knows:

  • All extraction functions and their correct signatures across languages
  • Configuration field names (for example, max_chars not max_characters in Python)
  • Rust feature gates (for example, tokio-runtime for sync functions)
  • Language-specific conventions (snake_case in Python/Rust, camelCase in Node.js)
  • Error handling patterns for each language

Quick Examples

from kreuzberg import extract_file, extract_file_sync, ExtractionConfig, OcrConfig

result = await extract_file("document.pdf")
print(result.content)

config = ExtractionConfig(
    ocr=OcrConfig(backend="tesseract", language="eng"),
    output_format="markdown",
)
result = await extract_file("document.pdf", config=config)

import { extractFile, extractFileSync } from '@kreuzberg/node';

const result = await extractFile('document.pdf');
console.log(result.content);

use kreuzberg::{extract_file, ExtractionConfig};

let config = ExtractionConfig::default();
let result = extract_file("document.pdf", None, &config).await?;

kreuzberg extract document.pdf
kreuzberg extract document.pdf --format json --output-format markdown

Further Reading

Edit this page on GitHub