deedy5/ddgs

A metasearch library that aggregates results from diverse web search services

What it solves

DDGS (Dux Distributed Global Search) is a metasearch library that allows users to aggregate search results from multiple web search engines simultaneously. It simplifies the process of gathering data from the web by providing a single interface for text, images, videos, news, and books search, as well as content extraction from URLs.

How it works

The library provides a DDGS class that acts as a wrapper around various search backends. Users can specify a backend (e.g., Google, Bing, DuckDuckGo, Brave, Yahoo) or set it to "auto" to let the library handle the selection. It offers several specialized search functions:

  • Text Search: Aggregates results from engines like Bing, Brave, DuckDuckGo, Google, Grokipedia, Mojeek, Startpage, Yandex, Yahoo, and Wikipedia.
  • Media Search: Provides dedicated functions for images, videos, and news.
  • Content Extraction: The extract() function fetches a URL and converts its content into various formats, such as Markdown, plain text, or raw HTML.

The project also provides an API server (via FastAPI) and an MCP (Model Context Protocol) server, making it easy to integrate these search tools into AI agents or other applications.

Who it’s for

Developers building AI agents, RAG (Retrieval-Augmented Generation) pipelines, and data gathering tools who need a unified, programmatic way to access multiple search engines without managing multiple individual APIs.

Highlights

  • Multi-Backend Support: Supports a wide array of search engines across different modalities (text, image, video, news, books).
  • AI-Ready Integration: Includes a built-in MCP server for direct integration with AI clients like Cursor or Claude Desktop.
  • Content Extraction: Built-in utility to convert web pages into AI-friendly Markdown format.
  • Flexible Deployment: Can be deployed as a Python library, a standalone API server, or via Docker Compose.

Related

  • Project
    spences10/mcp-omnisearch

    An MCP server that provides unified access to multiple web search, AI search, and web extraction tools including Tavily, Brave, Kagi, and Firecrawl.

  • Project
    nickclyde/duckduckgo-mcp-server

    An MCP server that enables AI models to search DuckDuckGo and fetch webpage content with built-in bot detection bypass and context-saving URL shortening.

  • Project
    TechyNilesh/DeepImageSearch

    A Python library for building AI-powered image search systems supporting text, image, and hybrid search using multimodal embeddings and vector indexing.

  • Project
    CodeGraphContext/CodeGraphContext

    A toolkit and MCP server that indexes local code repositories into a graph database to provide AI agents and developers with structural context like call chains and class hierarchies.

  • Project
    karust/openserp

    An open-source SERP API and CLI that provides structured search results from multiple search engines without API keys, designed for LLM grounding and SEO tracking.