# Octopods — everything on this site is open to crawling and indexing. # # The previous file allowed everything implicitly via an empty Disallow. That # still works, but naming the AI crawlers explicitly removes any ambiguity for # bots that look for their own token before falling back to the wildcard, and # makes the policy legible to anyone auditing the site. User-agent: * Allow: / # --- AI search and answer engines ------------------------------------------- # These fetch pages to answer user questions and cite sources. We want to be # citable, so they are allowed everywhere. User-agent: OAI-SearchBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: PerplexityBot Allow: / User-agent: Perplexity-User Allow: / User-agent: Claude-SearchBot Allow: / User-agent: Claude-User Allow: / User-agent: Google-Extended Allow: / User-agent: Applebot Allow: / User-agent: Applebot-Extended Allow: / User-agent: DuckAssistBot Allow: / User-agent: Amazonbot Allow: / User-agent: MistralAI-User Allow: / User-agent: YouBot Allow: / # --- AI training crawlers --------------------------------------------------- # Allowed as well: the site is public marketing content, and being present in # training data helps these models describe the product correctly. User-agent: GPTBot Allow: / User-agent: ClaudeBot Allow: / User-agent: anthropic-ai Allow: / User-agent: Meta-ExternalAgent Allow: / User-agent: xAI-Bot Allow: / User-agent: DeepseekBot Allow: / Sitemap: https://www.octopods.io/sitemap.xml