Tavily

OpenClaw can use Tavily in two ways:

• as the
  text

  Copy

  web_search
  provider
• as explicit plugin tools:
  text

  Copy

  tavily_search
  and
  text

  Copy

  tavily_extract

Tavily is a search API designed for AI applications, returning structured results optimized for LLM consumption. It supports configurable search depth, topic filtering, domain filters, AI-generated answer summaries, and content extraction from URLs (including JavaScript-rendered pages).

Get an API key

1. Create a Tavily account at tavily.com.
2. Generate an API key in the dashboard.
3. Store it in config or set
   text

   Copy

   TAVILY_API_KEY
   in the gateway environment.

Configure Tavily search

json5
Copy
{
  plugins: {
    entries: {
      tavily: {
        enabled: true,
        config: {
          webSearch: {
            apiKey: "tvly-...", // optional if TAVILY_API_KEY is set
            baseUrl: "https://api.tavily.com",
          },
        },
      },
    },
  },
  tools: {
    web: {
      search: {
        provider: "tavily",
      },
    },
  },
}

Notes:

• Choosing Tavily in onboarding or
  text

  Copy

  openclaw configure --section web
  enables the bundled Tavily plugin automatically.
• Store Tavily config under
  text

  Copy

  plugins.entries.tavily.config.webSearch.*
  .
• text

  Copy

  web_search
  with Tavily supports
  text

  Copy

  query
  and
  text

  Copy

  count
  (up to 20 results).
• For Tavily-specific controls like
  text

  Copy

  search_depth
  ,
  text

  Copy

  topic
  ,
  text

  Copy

  include_answer
  , or domain filters, use
  text

  Copy

  tavily_search
  .

Tavily plugin tools

text

Copy

tavily_search

Use this when you want Tavily-specific search controls instead of generic

.

Search depth:

text

Copy

tavily_extract

Use this to extract clean content from one or more URLs. Handles JavaScript-rendered pages and supports query-focused chunking for targeted extraction.

Extract depth:

Tips:

• Max 20 URLs per request. Batch larger lists into multiple calls.
• Use
  text

  Copy

  query
  +
  text

  Copy

  chunks_per_source
  to get only relevant content instead of full pages.
• Try
  text

  Copy

  basic
  first; fall back to
  text

  Copy

  advanced
  if content is missing or incomplete.

Choosing the right tool

Related

• Web Search overview -- all providers and auto-detection
• Firecrawl -- search + scraping with content extraction
• Exa Search -- neural search with content extraction