# https://www.gcleantech.com/robots.txt
# Green Cleaning Technology — permissive defaults for search + AI discovery.
# Host your site at the root so this file is served from https://www.gcleantech.com/robots.txt

User-agent: *
Allow: /

# Sitemaps
Sitemap: https://www.gcleantech.com/sitemap.xml

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

User-agent: Googlebot-Image
Allow: /

# Google-Extended is used for AI training/discovery products including Gemini-related systems.
User-agent: Google-Extended
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common AI / research crawlers (allow site facts to be cited accurately)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: cohere-ai
Allow: /

# Optional: slow aggressive scrapers (uncomment to block if abused)
# User-agent: AhrefsBot
# Disallow: /