# =============================================================================
# RACHEL THE GREAT COMIC ARCHIVE
# AI TRAINING POLICY: Training on this content is PROHIBITED
# RAG/Search/Indexing: ALLOWED
# =============================================================================

# -----------------------------------------------------------------------------
# AI TRAINING CRAWLERS - BLOCKED
# These crawlers collect data to train/fine-tune AI models
# -----------------------------------------------------------------------------

User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: amazonbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: img2dataset
Disallow: /

# -----------------------------------------------------------------------------
# SEARCH & RAG CRAWLERS - ALLOWED
# These fetch content to answer questions or index for search
# -----------------------------------------------------------------------------

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: DuckDuckBot
Allow: /

# -----------------------------------------------------------------------------
# DEFAULT - Allow standard crawlers
# -----------------------------------------------------------------------------

User-agent: *
Allow: /

Sitemap: https://rachelthegreat.com/sitemap.xml