search▌

Semantic search finds content by meaning rather than exact keywords. An embedding model converts text into high-dimensional vectors, where similar meanings map to nearby points. pgvector stores these vectors in PostgreSQL and uses approximate nearest neighbor (ANN) indexes to find the closest matches quickly—scaling to millions of rows without leaving the database. Store your text alongside its embedding, then query by converting your search text to a vector and returning the rows with the small

Unified search with automatic provider selection across seven search engines. \n \n Intelligently routes queries to the best provider: Serper for shopping, Tavily for research, Exa for semantic similarity, Perplexity for direct answers with citations, You.com for real-time info, Querit for multilingual searches, and SearXNG for privacy \n Requires only one API key to start; all provider keys are optional and can be added incrementally \n Includes automatic fallback to alternate providers on rate

You are a search specialist expert at finding and synthesizing information from the web.

Web search with ranked results, snippets, and support for freshness filters, SafeSearch, and custom ranking via Goggles. \n \n Returns structured results across multiple types: web pages, news, videos, discussions, FAQ, infobox, and locations in a single response \n Supports freshness filtering (past day/week/month/year or custom date ranges), SafeSearch levels, and location-aware results via headers \n Goggles enable custom result ranking: boost trusted sources, suppress spam, or build focused

Search and discover paid API services available on the x402 bazaar marketplace. \n \n Query the marketplace using BM25 relevance search, list all available resources, or inspect specific endpoints to see pricing and payment requirements without paying \n Supports filtering by network (base, base-sepolia) and output formats (human-readable or JSON) \n Results are cached locally and auto-refresh every 12 hours; no authentication required for any search or discovery operation \n Use as a fallback w

Web search with LLM-optimized results, relevance scoring, and flexible filtering. \n \n Supports four search depth modes (ultra-fast, fast, basic, advanced) with configurable latency and relevance tradeoffs \n Includes domain filtering, time range constraints, date ranges, country boosting, and raw content extraction \n Returns results with title, URL, content snippet, and relevance score; optional image results and favicons \n Automatic OAuth authentication via Tavily MCP server or API key conf

Google searches via real browser sessions, extracting live results while reusing logged-in credentials to minimize CAPTCHAs. \n \n Launches Google searches in real browser mode to leverage existing user sessions and reduce bot detection blocks \n Provides commands to inspect search results, click through to individual pages, and extract content summaries with source citations \n Includes fallback to Jina AI text extraction if browser parsing encounters difficulties \n Requires browser-use instal

Search and explore Windows desktop APIs with full type signatures and members. \n \n Indexes Windows Platform SDK, WinAppSDK, NuGet packages, and project-output WinMD files; Platform SDK and WinAppSDK are available immediately on fresh clones without restore or build \n Two workflows: discover mode for finding the right API by capability keywords, and lookup mode for retrieving exact methods, properties, events, and enum values of known types \n Requires .NET SDK 8.0+ and a one-time cache genera

Expert guidance for implementing Mapbox search functionality in applications. Covers the complete workflow from asking the right discovery questions, selecting the appropriate search product, to implementing production-ready integrations following best practices from the Mapbox search team.

Neural search across web, code, and company research without API keys. \n \n Three core tools: web search for news and facts, code search for GitHub and Stack Overflow examples, and company research for business intelligence \n Configurable search depth with type parameter (\"fast\" or \"deep\") for web queries and adjustable token ranges (1000–50000) for code context \n Optional advanced tools available via config update, including domain/date filtering, query expansion, full page crawling, peo