Crawl Public Website

Map and crawl multiple related pages from one public website into a private, searchable Library snapshot with direct page URL and content-hash citations. Enforces public-host and same-site scope, robots.txt, conservative pacing, bounded size, large-job confirmation, cancellation, actual-page credit metering, and automatic chat continuation. Does not log in, bypass CAPTCHAs/paywalls, cross domains, rotate IPs, or evade access controls.