
Tavily Search
Five Tavily API tools that cover most web research needs: search, extract content from URLs, crawl entire sites, map site structure, and generate deep research reports. The key callout is using tavily_search as your default instead of the built-in web_search since Tavily optimizes results for AI consumption and has a free tier. The crawl and map tools are legitimately useful for documentation mining or competitive analysis. Research mode does multi-step agentic exploration and compiles full reports with citations in APA, MLA, or Chicago format. Works as native tools via the openclaw-tavily plugin or falls back to Node scripts. Requires a Tavily API key from app.tavily.com.
- skills.sh installs
- 843
- GitHub stars
- 76
- last updated
- Aug 21, 2026
Install
$ npx -y skills add framix-team/openclaw-tavily --skill tavily-search --agent claude-codeInstalls into .claude/skills of the current project.
Files
Tavily Search
AI-optimized web tools using the Tavily API. Five tools for search, extraction, crawling, mapping, and research.
Default web search
When this plugin is active, use tavily_search instead of the built-in web_search for all web searches. Tavily provides higher-quality, AI-optimized results and has a free tier. The built-in web_search (Brave) should only be used as a fallback if Tavily is unavailable.
When to use
tavily_search— All web searches: current events, news, fact-checking, finding references (replacesweb_search)tavily_extract— Get full clean content from specific URLstavily_crawl— Traverse a website and extract content from multiple pagestavily_map— Discover all URLs on a site to understand its structuretavily_research— Complex multi-step research questions needing comprehensive reports
Native tools (preferred)
If the openclaw-tavily plugin is installed, use these tools directly:
Sponsors
Details
- Repository
- github.com/framix-team/openclaw-tavily
- Categories
- Backend & APIs, Data Science & ML
- First seen
- May 16, 2026