tavily▌

Multi-page website crawler with semantic filtering and markdown export. \n \n Crawl entire site sections with depth and breadth control; filter by path regex, domain, or natural language instructions to focus results \n Save each page as local markdown files via --output-dir , or return structured JSON for agentic processing \n Use semantic instructions with chunk extraction to prevent context bloat when feeding results to LLMs; use full-page extraction for offline documentation downloads \n Sup

Extract clean markdown or text from up to 20 URLs, with JavaScript rendering and query-focused chunking support. \n \n Handles JavaScript-rendered pages with configurable extraction depth (basic for simple pages, advanced for dynamic SPAs and tables) \n Supports query-focused extraction to return only relevant content chunks instead of full pages \n Returns LLM-optimized markdown by default, with options for plain text format and structured JSON output \n Processes up to 20 URLs in a single call

Web search, content extraction, site crawling, and deep research via Tavily CLI. \n \n Five command modes covering search, extraction, URL discovery, bulk crawling, and multi-source research with citations \n All commands support JSON output and file saving for structured, agentic workflows \n Escalation pattern guides you from simple search through extraction, mapping, crawling, to comprehensive research based on your needs \n Requires tavily-cli installation and API key authentication via tvly

$1f

Comprehensive AI-powered research with multi-source synthesis and citations. \n \n Produces structured reports grounded in web sources, taking 30-120 seconds depending on model selection (mini for targeted queries, pro for complex comparisons) \n Supports multiple output formats: markdown reports, JSON with custom schemas, and configurable citation styles (numbered, MLA, APA, Chicago) \n Includes async workflow for long-running research via --no-wait , status , and poll commands, plus real-time