{"id":"ddgs","name":"DDGS","homepage":"https://github.com/deedy5/ddgs","repo_url":"https://github.com/deedy5/ddgs","category":"ai-ml","subcategories":["web-search","metasearch","information-retrieval"],"tags":["search","metasearch","duckduckgo","google","bing","brave","mcp","web-search","news-search","image-search","video-search"],"what_it_does":"Metasearch Python library that aggregates results from multiple search engines (Bing, Brave, DuckDuckGo, Google, Mojeek, Yandex, Yahoo, Wikipedia) into a unified interface. Supports text, image, video, news, and book searches. Includes an MCP server with HTTP and SSE transports, plus a standalone API server.","use_cases":["AI agent web search via MCP without per-query API costs","Aggregated multi-engine search for better coverage","News monitoring and research across multiple sources","Image and video search for AI workflows","Book discovery via Anna's Archive integration"],"not_for":["High-volume production search (may hit rate limits from upstream engines)","Guaranteed search result freshness or completeness","Enterprise search with SLAs"],"best_when":"You need free, multi-engine web search for AI agents without paying per-query API fees to commercial search providers.","avoid_when":"You need guaranteed uptime, official API access with SLAs, or very high query volumes. Commercial search APIs (Tavily, Brave Search API) may be more reliable.","alternatives":["tavily-mcp","brave-search-mcp","exa-mcp-server","searxng"],"af_score":61.5,"security_score":60.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":"unknown","last_evaluated":"2026-03-01T09:50:05.480053+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":"Depends on upstream search engine rate limits. Proxy support helps avoid throttling.","data_source":"llm_estimated","measured_on":null}}