# https://www.robotstxt.org/robotstxt.html
User-agent: *
Disallow:
# AI search crawlers — explicit allow for citation-driving bots.
# Without explicit Allow lines, some bots interpret missing rules as
# implicit disallow.
User-agent: GPTBot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: Claude-User
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: Applebot-Extended
Allow: /
# Common Crawl: feeds LLM training corpora. Disallow by default —
# training-data inclusion does not drive citations and we have no
# control over how the data is used. Switch to Allow if brand presence
# in training corpora becomes a goal.
User-agent: CCBot
Disallow: /
# Sitemap reference
Sitemap: https://protofire.io/sitemap.xml