Agent Plugins Marketplace
← All plugins

kreuzberg

v0.2.2

Local document extraction: text, tables, metadata, images from 91+ formats with optional OCR.

Codex7 Skills

By Kreuzberg, Inc.License: MIT1.1k GitHub starsUpdated 14 hours ago

Directory evidence

Runtimes
Codex
Parsed components
7 skill or MCP entries
Source updated
Sep 23, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install kreuzberg for Codex

Installs for the current user
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add kreuzberg@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/hashgraph-online/awesome-codex-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/kreuzberg-dev/plugins/plugins/kreuzberg/.

Plugin files

plugins/kreuzberg-dev/plugins/plugins/kreuzberg/
├── .codex-plugin/plugin.json
├── skills/batch-extraction/SKILL.md
├── skills/chunking/SKILL.md
├── skills/extracting-keywords/SKILL.md
├── skills/extracting-tables/SKILL.md
├── skills/extracting-with-ocr/SKILL.md
├── skills/kreuzberg/SKILL.md
└── skills/picking-a-format/SKILL.md

Included Skills7

batch-extractionskills/batch-extraction/SKILL.md

Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command, `--file-configs`, `--max-concurrent`, and output layout.

chunkingskills/chunking/SKILL.md

Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone `chunk` command.

extracting-keywordsskills/extracting-keywords/SKILL.md

Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gating), `--detect-language`, and the standalone `embed` command with real flags.

extracting-tablesskills/extracting-tables/SKILL.md

Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.

extracting-with-ocrskills/extracting-with-ocr/SKILL.md

Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.

kreuzbergskills/kreuzberg/SKILL.md

Extract text, tables, metadata, and images from 91+ document formats (PDF, Office, images, HTML, email, archives, academic) using Kreuzberg. Use when writing code that calls Kreuzberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins.

picking-a-formatskills/picking-a-format/SKILL.md

Use when choosing an output format for extracted documents — text, markdown, djot, html, or JSON. Maps consumer (LLM, parser, archive) to the right `--format` / `--content-format` pair.

Plugin manifests1

plugins/kreuzberg-dev/plugins/plugins/kreuzberg/.codex-plugin/plugin.json
{
  "name": "kreuzberg",
  "version": "0.2.2",
  "description": "Local document extraction: text, tables, metadata, images from 91+ formats with optional OCR.",
  "author": {
    "name": "Kreuzberg, Inc.",
    "email": "[email protected]",
    "url": "https://kreuzberg.dev"
  },
  "homepage": "https://kreuzberg.dev",
  "repository": "https://github.com/kreuzberg-dev/plugins",
  "license": "MIT",
  "keywords": [
    "document-intelligence",
    "extraction",
    "ocr",
    "pdf",
    "tables"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Kreuzberg",
    "shortDescription": "Local document extraction for 91+ formats",
    "longDescription": "Extract text, tables, metadata, and images from PDFs, Office files, images, HTML, email, archives, and academic formats. Runs locally via the kreuzberg CLI and an auto-registered MCP server. Plugin ships skills covering the CLI surface, OCR backends, table extraction, and output-format selection.",
    "developerName": "Kreuzberg, Inc.",
    "category": "document-intelligence",
    "capabilities": [
      "Read"
    ],
    "defaultPrompt": [
      "Extract text from this PDF",
      "OCR a scanned image",
      "List supported formats"
    ],
    "websiteURL": "https://kreuzberg.dev",
    "privacyPolicyURL": "https://kreuzberg.dev/privacy",
    "termsOfServiceURL": "https://kreuzberg.dev/terms",
    "brandColor": "#1F6FEB",
    "composerIcon": "./assets/icon.svg",
    "logo": "./assets/logo.png",
    "screenshots": []
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[kreuzberg on Agent Plugins Marketplace](https://pluginsmp.com/plugins/kreuzberg)