tavily
Tavily is an AI-optimized search engine built for language model applications that need current web data. It provides web search, URL content extraction, site crawling, and autonomous research capabilities—all designed to return results formatted for LLM consumption rather than human browsing.
Tavily integrates real-time web search into LLM applications with built-in content extraction and AI-guided crawling.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-18
Tavily integrates real-time web search into LLM applications with built-in content extraction and AI-guided crawling. Tavily is an AI-optimized search engine built for language model applications that need current web data. It provides web search, URL content extraction, site crawling, and autonomous research capabilities—all designed to return results formatted for LLM consumption rather than human browsing.
Use it when
- Tavily is an AI-optimized search engine built for language model applications.
- Yes.
Verify before relying
Read SKILL.md below before installing (6 files). Open directory: indexed for reading, not audited.
Install
itechmeat/llm-code/tavily · repository language: Go
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I integrate real-time search into AI apps with tavily?
Tavily provides an API and Python SDK designed specifically for LLM integration. Install the tavily-python package, authenticate with your API key, and use tavily's search methods to fetch current web results formatted for language model consumption. Tavily returns structured data optimized for AI processing rather than human-readable web pages, making it ideal for building agents and applications that need live information.
What is tavily and how does it differ from standard search?
Tavily is an AI-optimized search engine built for language model applications. Unlike general search engines, tavily returns results formatted specifically for LLM consumption, with built-in content extraction, relevance ranking tuned for AI tasks, and support for autonomous research workflows. It handles web search, URL content extraction, site crawling, and complex topic research—all designed to feed current data directly into AI systems.
Can I extract content from URLs with tavily?
Yes. Tavily provides content extraction capabilities that let you programmatically pull and process text from web pages. This is particularly useful for building RAG (Retrieval-Augmented Generation) systems that need to ingest current web data. Tavily handles the extraction and formatting, returning clean content ready for embedding and retrieval workflows.
How do I build a RAG pipeline with web data using tavily?
Tavily enables RAG systems by providing real-time web search and content extraction. Search for relevant topics using tavily's API, extract full page content from the results, embed the extracted text into your vector store, and retrieve it during generation. Tavily's AI-optimized results and structured output make it straightforward to integrate current web knowledge into your RAG application.
Does tavily support website crawling and site mapping?
Tavily supports crawling and mapping website structure with AI guidance. You can use tavily to explore sites programmatically, extract content from multiple pages, and build structured maps of site hierarchies. This is useful for research tasks, competitive analysis, and building knowledge bases from specific domains.
What license does tavily use?
Tavily is released under the MIT license, allowing free use, modification, and distribution in both open-source and commercial projects with minimal restrictions.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Tavily
AI-optimized search engine for building LLM applications with real-time web data.
Links
Quick Navigation
| Topic | Reference |
|---|---|
| REST API | api.md |
| Python SDK | python.md |
| JavaScript SDK | javascript.md |
| Best Practices |
(truncated - see the full file via the links below)
File tree — 6 files
skills/tavily/SKILL.md
skills/tavily/references/api.md
skills/tavily/references/best-practices.md
skills/tavily/references/integrations.md
skills/tavily/references/javascript.md
skills/tavily/references/python.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Integrate real-time web search into LLM applications”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Tavily wraps the Tavily REST API to enable web search, content extraction, site discovery, and crawling directly from your agent. It returns structured results with titles, URLs, and summaries designed for downstream LLM use, and supports optional research workflows with citations when deeper investigation is needed.
Tavily Web integrates the Tavily API to handle multiple research workflows: search the web for current information, extract and summarize content from specific URLs, crawl sites to discover page structure, and generate structured research output. Route requests to the appropriate endpoint based on user intent—search for latest sources, extract for URL content, crawl for site traversal, map for page discovery, or research for schema-driven results.
Learn to build production Tavily integrations with patterns for web search, URL content extraction, site crawling, and AI-synthesized research. Covers SDK setup, method selection, async patterns, and framework integrations for agents and RAG systems.
This skill documents how to build production Tavily integrations for AI agents and LLM applications. It covers web search, URL content extraction, site-wide crawling, URL discovery, and AI-powered research across Python and JavaScript SDKs with async support and framework integrations.
Tavily Search queries the entire web and returns ranked results with relevance scores and optional AI-generated answers in one call. Unlike single-URL fetching, it powers research workflows, competitive analysis, and "what's the latest" questions with configurable search depth, time ranges, and content extraction across multiple pages.
Tavily provides a web search API purpose-built for AI agents, returning organized results that LLMs can consume directly. It supports both quick and deep search modes, with configurable result limits and domain filtering to suit different research needs.
More skills web-search-tavily (MIT) · tavily-research (MIT) · Tavily (NOASSERTION)