Give a local agent web access without paid search APIs

A can get web access without using paid services such as Tavily, Serper, or Firecrawl. The setup uses two simple tools: one for search and one for page . Search runs through SearXNG, a meta started in Docker, and the agent calls its .

Each search result is reduced to a title, URL, and description. The description is only a search snippet, not the page content, so it is not enough when the agent needs to read the full page. For page , Scrapling and Trafilatura are used together, with a fast path that fetches normal pages without launching a browser.

SearXNG must have JSON enabled in its settings, and public SearXNG instances are usually a poor fit for automated program use.

Key points

  • The setup gives a web access without paid search or scraping APIs.
  • SearXNG handles search through a .
  • Search snippets are not full page content, so a separate step is needed.
  • Scrapling and Trafilatura handle page .
  • Public SearXNG instances are usually not suitable for automated agent use.
Read original