Ddgs

ddgs is a metasearch engine and web content extractor that provides a toolkit for programmatically retrieving search results from DuckDuckGo. It functions as a search API server and a Model Context Protocol server to integrate web search capabilities directly into large language model environments.

The project distinguishes itself by aggregating text, image, news, and video results from multiple providers into a single interface. It includes a utility for fetching URLs and converting HTML content into markdown, plain text, or structured data.

The system covers a broad range of search capabilities, including specialized searches for books and filtered searches for images and videos. It provides a command line interface for information retrieval, search data export to JSON and CSV, and the ability to define custom search provider extensions.

The project can be deployed as a containerized service with integrated health checks and proxy support.

Features

MCP Servers - Implements a Model Context Protocol server that exposes web search tools to large language models.

Metasearch Engines - Aggregates results from multiple external search providers into a single unified interface.

Model Context Protocol Integrations - Integrates web search capabilities into AI models via the Model Context Protocol for grounded responses.

Model Context Protocol Implementations - Implements the Model Context Protocol to connect search logic to AI models using standard I/O streams.

Web Content Extraction Utilities - Fetches URLs and converts HTML content into markdown, plain text, or rich text formats.

Web Page Markdown Converters - Converts rendered web page HTML into clean markdown for data processing and AI analysis.

Web Search APIs - Exposes search functionality via a containerized web API server with automatic documentation.

Structured Search Retrieval - Provides a toolkit for the structured retrieval of search results from DuckDuckGo without an official API.

Text Search - Aggregates text-based search results from multiple backends with region, safety, and time filters.

Web Search Engines - Combines results from multiple web search services into a single interface for comprehensive information retrieval.

Search Result Aggregators - Combines search results from multiple different search engines into a single unified interface.

Web Search Integrations - Integrates real-time web search results into custom applications through a dedicated API server.

Search Aggregators - Queries multiple search services simultaneously to normalize text, image, news, video, and book results.

CLI Search Interfaces - Provides a command line interface for executing web search queries and managing result limits.

Web Content Extractors - Fetches URLs and converts HTML content into markdown, plain text, or structured data for LLM consumption.

HTML to Markdown Converters - Transforms raw HTML web page source into cleaned markdown for better LLM consumption.

Terminal Search Utilities - Enables quick web searches and data gathering directly from the terminal.

Web Page Retrievers - Programmatically retrieves primary text and structured data from specific URLs.

deedy5ddgs

Features

Star history