tavily
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.
Tavily is an AI-optimized web search API that returns structured results ready for LLM consumption.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-03-18
Tavily is an AI-optimized web search API that returns structured results ready for LLM consumption. 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.
Use it when
- Tavily requires an API key to authenticate requests.
- Yes—tavily is specifically designed to deliver structured, clean search results optimized for LLM consumption.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
malue-ai/dazee-small/tavily · repository language: Python
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
What is tavily and how does it work as a web search API?
Tavily is a web search API purpose-built for AI agents and LLMs. It returns organized, structured results that language models can consume directly without parsing raw HTML. Tavily supports both quick and deep search modes, letting you choose between fast answers and comprehensive research depending on your use case.
How do I set up tavily search with an API key?
Tavily requires an API key to authenticate requests. Once you obtain your key from Tavily's platform, you can integrate it into your application using the Python SDK or REST API. The key is passed with each request to enable AI-optimized search queries tailored for LLM agent integration.
Can tavily provide structured web search results for LLM?
Yes—tavily is specifically designed to deliver structured, clean search results optimized for LLM consumption. Instead of returning raw web pages, tavily formats results in a machine-readable structure that AI agents can parse and reason over directly, eliminating the need for additional data cleaning.
What search depth options does tavily offer?
Tavily supports configurable search depth with basic and advanced modes. Basic mode returns quick answers for simple queries, while advanced mode performs deeper research with more comprehensive coverage. You can also set max results limits and apply domain filtering to tailor the research backend to your specific information retrieval needs.
How does tavily compare to other web search solutions?
Tavily replaces basic search backends with higher-quality, AI-optimized results specifically engineered for agent workflows. Unlike general search engines, tavily prioritizes structured output and LLM-friendly formatting, making it ideal for deep research tasks where clean, organized data matters more than raw result volume.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Tavily AI 搜索
专为 AI Agent 优化的搜索 API，返回干净、结构化的结果，适合 LLM 直接消费。
使用场景
- 需要高质量搜索结果用于调研、写作等复杂任务
- ddg-search 结果不够精确时的升级选项
- deep-research 流程中的搜索后端
前置条件
需要设置环境变量 TAVILY_API_KEY：
1. 访问 https://tavily.com/ 注册（免费套餐每月 1000 次）
2. 设置：export TAVILY_API_KEY="tvly-xxxxx"
执行方式
基本搜索
curl -s -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-d '{
"api_key": "'$TAVILY_API_KEY'",
"query": "搜索内容",
"search_depth": "basic",
"max_results": 5
}'
深度搜索
curl -s -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-d '{
"api_key": "'$TAVILY_API_KEY'",
"query": "搜索内容",
"search_depth": "advanced",
"max_results": 10,
"include_raw_content": true
}'
Python SDK
```python from tavily import TavilyClient
client =
(truncated - see the full file via the links below)
File tree — 1 file
skills/library/tavily/SKILL.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 › “Find AI-optimized web search API for LLM agent integration”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Query the web and retrieve ranked results optimized for language models using Tavily's search API. Configure search depth, time ranges, domain filters, and result limits to fit your agent's needs. Supports OAuth or API key authentication with no manual setup required.
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 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 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.
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.
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.
More skills tavily-web (MIT) · tavily-research (MIT) · Tavily Extract (unlicensed)