# CloudNSite robots.txt
# https://cloudnsite.com

# Default - Allow all
User-agent: *
Allow: /

# Traditional Search Engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# Social Media Crawlers
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Pinterestbot
Allow: /

# OpenAI Crawlers
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic Crawlers
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Anthropic-AI
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Anthropic (current identifiers; Claude-Web above is the legacy name)
User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Perplexity user-initiated fetches (documented as generally ignoring
# robots.txt, listed here so the intent is explicit either way)
User-agent: Perplexity-User
Allow: /

# Google AI
User-agent: Google-Extended
Allow: /

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

# Cohere
User-agent: cohere-ai
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Common Crawl
User-agent: CCBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

# ByteDance
User-agent: Bytespider
Allow: /

# Sitemap location
Sitemap: https://cloudnsite.com/sitemap.xml

# LLMs.txt for AI crawlers
LLMs-Txt: https://cloudnsite.com/llms.txt

# AI Plugin (future-proofing)
AI-Plugin: https://cloudnsite.com/.well-known/ai-plugin.json