{
 "slug": "omgilibot",
 "name": "omgilibot",
 "operator": "Webz.io",
 "operator_slug": "webz",
 "category": "dataset",
 "category_label": "Corpus and dataset builders",
 "robots_token": "omgilibot",
 "user_agent_substring": "omgilibot",
 "user_agent_example": "omgilibot/0.4; +http://omgili.com",
 "respects_robots_txt": "documented",
 "respects_robots_txt_label": "obeys robots.txt (documented)",
 "verification_method": "none",
 "verification_label": "no published verification method",
 "published_ip_ranges_url": null,
 "ip_ranges_endpoint": null,
 "ipv4_prefix_count": 0,
 "ipv6_prefix_count": 0,
 "what_it_is": "Webz.io's crawler, collecting web and forum text sold as datasets, including to model builders.",
 "cost_of_blocking": "Exclusion from a commercial dataset resold to third parties.",
 "operator_docs": "https://webz.io/blog/machine-learning/",
 "html_url": "https://www.pathwren.workers.dev/crawler/omgilibot.html",
 "json_url": "https://www.pathwren.workers.dev/crawler/omgilibot.json",
 "last_reviewed": "2026-09-01"
}