🐲📚 Documentation Search Engine - An intelligent documentation search and extraction tool that provides both a command-line interface for humans and an MCP (Model Context Protocol) server for AI agents. Search across Sphinx, MkDocs, Pydoctor, and Rustdoc sites with fuzzy matching, extract clean markdown content, and integrate seamlessly with AI development workflows.

• 🔍 Universal Search: Fuzzy, exact, and regex search across documentation inventories and full content
• 🤖 AI Agent Ready: Built-in MCP server for seamless integration with Claude Code and other AI tools
• 📖 Multi-Format Support: Works with Sphinx, MkDocs, Pydoctor, and Rustdoc sites
• 🚀 High Performance: In-memory caching with sub-second response times for repeated queries
• 🧹 Clean Output: High-quality HTML-to-Markdown conversion preserving code blocks and formatting
• 🎯 Auto-Detection: Automatically identifies documentation type without manual configuration
• 🔌 Extensible: Plugin architecture supports additional documentation formats via extension manager

Add as an MCP server in your AI client configuration. For example, in Claude Code's MCP configuration:

{
  "mcpServers": {
    "librovore": {
      "command": "uvx",
      "args": [
        "librovore",
        "serve"
      ]
    }
  }
}

Download the latest standalone executable for your platform from GitHub Releases. These executables have no dependencies and work out of the box.

Install via the uv tool command:

uv tool install librovore

or, run directly with uvx:

uvx librovore

Or, install via pipx:

pipx install librovore

Install via uv pip command:

uv pip install librovore

Or, install via pip:

pip install librovore

Search Python documentation for 'pathlib':

librovore query-inventory https://docs.python.org/3 pathlib

Search content with fuzzy matching:

librovore query-content https://fastapi.tiangolo.com "dependency injection"

Start the MCP server for AI agent integration:

librovore serve

The server provides tools for AI agents to search documentation object inventories, search full documentation content with snippets, and get overviews of available documentation.

• AI Development: Enable Claude Code and other AI agents to search technical documentation
• Documentation Research: Quickly find API references and usage examples across multiple sites
• Development Workflows: Access documentation programmatically during development
• Cross-Reference Search: Find related concepts across different documentation sources

The name "librovore" draws from Latin roots meaning "book-devourer" - a fitting metaphor for a tool that consumes and digests documentation across multiple formats:

• 📚 Anglicized Latin libro- ("book") + -vore ("devouring")
• 🐲 The "Book Wyrm" - traditionally "librovore" is a synonym for "bookworm", but Claude's choice of the dragon emoji 🐲 rather than a worm emoji transformed our humble bookworm into a legendary wyrm that devours knowledge and makes it accessible
• 📖 Both "worm" and "wyrm" share the same Old English origins, so the linguistic evolution fits perfectly

Contribution to this project is welcome! However, it must follow the code of conduct for the project.

Please file bug reports and feature requests in the issue tracker or submit pull requests to improve the source code or documentation.

For development guidance and standards, please see the development guide.

• python-absence (absence on PyPI)

  🕳️ A Python library package which provides a sentinel for absent values - a falsey, immutable singleton that represents the absence of a value in contexts where None or False may be valid values.

• python-accretive (accretive on PyPI)

  🌌 A Python library package which provides accretive data structures - collections which can grow but never shrink.

• python-classcore (classcore on PyPI)

  🏭 A Python library package which provides foundational class factories and decorators for providing classes with attributes immutability and concealment and other custom behaviors.

• python-detextive (detextive on PyPI)

  🕵️ A Python library which provides consolidated text detection capabilities for reliable content analysis. Offers MIME type detection, character set detection, and line separator processing.

• python-dynadoc (dynadoc on PyPI)

  📝 A Python library package which bridges the gap between rich annotations and automatic documentation generation with configurable renderers and support for reusable fragments.

• python-falsifier (falsifier on PyPI)

  🎭 A very simple Python library package which provides a base class for falsey objects - objects that evaluate to False in boolean contexts.

• python-frigid (frigid on PyPI)

  🔒 A Python library package which provides immutable data structures - collections which cannot be modified after creation.

• python-icecream-truck (icecream-truck on PyPI)

  🍦 Flavorful Debugging - A Python library which enhances the powerful and well-known icecream package with flavored traces, configuration hierarchies, customized outputs, ready-made recipes, and more.

• python-mimeogram (mimeogram on PyPI)

  📨 A command-line tool for exchanging collections of files with Large Language Models - bundle multiple files into a single clipboard-ready document while preserving directory structure and metadata... good for code reviews, project sharing, and LLM interactions.