Ross ROSS = Recommend OSS · open-source software intelligence for agents

deedy5/ddgs

A metasearch library that aggregates results from diverse web search services observed · 2026-08-28

github.com/deedy5/ddgs · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

95/100

  • Activity 99
  • Release rhythm 87
  • Longevity 100
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 4.0
  • age_days: 1956
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 83

Full methodology

Adoption not part of the score

2915 stars · 278 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

DDGS (Dux Distributed Global Search) is a Python metasearch library that aggregates text, image, video, news, and book results from multiple web search backends such as Bing, Brave, DuckDuckGo, Google, and Yandex. It also ships as a CLI, a FastAPI-based REST API server, and an MCP server for integration with LLM clients like Claude Desktop and Cursor.

Use cases

  • search the web from python without api keys
  • aggregate search results from multiple engines
  • add web search to an llm agent via mcp
  • self-host a rest api for web search
  • scrape search results for research or data collection
  • extract page content from a url
  • search images news videos and books programmatically

When to choose

  • you need programmatic web search in Python across many engines with one interface
  • you want to give LLM clients like Claude Desktop or Cursor web search via MCP
  • you want a self-hosted search API with Docker or FastAPI
  • you need proxy support (e.g. Tor socks5) for search requests

When to avoid

  • you need a general-purpose web crawler rather than search result aggregation
  • you require official, contractually sanctioned access to a specific engine's results
  • you need guaranteed result quality or SLAs, since scraping-based backends can break or be rate-limited
  • you need a JavaScript or non-Python search client

Facets

library · maturity active

search-engine web-scraping mcp http-server cli developer-tools artificial-intelligence web-development python cli self-hosted cross-platform metasearch duckduckgo web-search-api fastapi mcp-server search-aggregation proxy-support search docker

2 sources

Member repositories

RepositoryRoleHealth v2
deedy5/ddgsmain95

For agents

markdown · JSON · MCP: product_card(name="deedy5/ddgs")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem