Skip to main content

Web Search

The agent can search the live web on its own. By default this is backed by a server-side proxy so you don't carry a search API key.

What it's good for​

  • Research - "what's the latest on X"
  • Citation hunting - "find me three sources for Y"
  • Fact-checking - the agent runs a quick search if it isn't confident

Self-hosted SearXNG​

If you run your own SearXNG instance, you can enable searxng_search as a private, self-hosted search tool.

Configure in config.toml:

[searxng]
enabled = true
base_url = "http://localhost:8080"
max_results = 10
default_language = "en"
timeout_seconds = 10

Or via environment:

OPENHUMAN_SEARXNG_ENABLED=true
OPENHUMAN_SEARXNG_BASE_URL=http://localhost:8080

How it differs from generic HTTP​

A pure http_request tool can fetch a URL but can't find one. Web Search is the discovery layer: it picks the right URLs for the agent, which then hands them off to the Web Scraper for the actual reading.

See also​