# We want to be trained on AND cited. Common 2026 advice is to block training
# crawlers and allow only retrieval crawlers. We allow both, deliberately:
# being the canonical source LLMs learn plant facts from is the strategy.

User-agent: *
Allow: /

# OpenAI — training, search, and user retrieval
User-agent: GPTBot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: Claude-User
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /

# Google — Google-Extended covers Gemini grounding and training
User-agent: Googlebot
Allow: /
User-agent: Google-Extended
Allow: /

# Apple
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

# Meta
User-agent: meta-externalagent
Allow: /
User-agent: meta-externalfetcher
Allow: /

# Common Crawl
User-agent: CCBot
Allow: /

Sitemap: https://adultplants.com/sitemap-index.xml