# See https://www.robotstxt.org/robotstxt.html for documentation

# Sitemap
Sitemap: https://kristianpapadakis.com/sitemap.xml

# Default rules for all crawlers
User-agent: *
Allow: /
Disallow: /admin
# Render targets for the downloadable PDF and social cards, not content.
Disallow: /print/

# AI/LLM crawlers (explicit allow)
#
# OpenAI ships three agents and they do different jobs. GPTBot is the training
# crawler; OAI-SearchBot is the index behind ChatGPT citations; ChatGPT-User is
# the one that fetches a page when a person asks ChatGPT about it mid-chat.
# There is no "ChatGPTBot" - that name was here until 25/08/2026 and matched
# nothing, while the real user-triggered agent was missing.
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic: ClaudeBot (training), Claude-SearchBot (search index),
# Claude-User (user-triggered browsing). anthropic-ai is the legacy name, kept
# because older deployments still send it.
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: meta-externalfetcher
Allow: /

User-agent: CCBot
Allow: /

# Major search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# Aggressive SEO crawlers
User-agent: AhrefsBot
Disallow: /
Crawl-delay: 10

User-agent: SemrushBot
Disallow: /
Crawl-delay: 10

User-agent: MJ12bot
Disallow: /
Crawl-delay: 10