# robots.txt to explicitly ALLOW all AI/LLM crawlers and other bots
# Last updated: 15 September 2025

# --- OpenAI ---
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# --- Anthropic ---
User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: claude-web
Allow: /

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

User-agent: Perplexity-User
Allow: /

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

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

User-agent: Applebot-Extended
Allow: /

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

User-agent: GoogleOther
Allow: /

# --- Meta (Facebook) ---
User-agent: FacebookBot
Allow: /

User-agent: meta-externalagent
Allow: /

# --- ByteDance ---
User-agent: ByteSpider
Allow: /

# --- Common Crawl ---
User-agent: CCBot
Allow: /

# --- Diffbot ---
User-agent: Diffbot
Allow: /

# --- DuckDuckGo ---
User-agent: DuckAssistBot
Allow: /

# --- Amazon ---
User-agent: Amazonbot
Allow: /

# --- LinkedIn ---
User-agent: LinkedInBot
Allow: /

# --- Mistral ---
User-agent: MistralAI-User
Allow: /

# --- Allen Institute ---
User-agent: AI2Bot
Allow: /

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

# --- DeepSeek ---
User-agent: DeepSeekBot
Allow: /

# --- Elon Musk / xAI (Grok) ---
User-agent: GrokBot
Allow: /

# --- Catch-all (all other crawlers not explicitly listed) ---
User-agent: *
Disallow:

Sitemap: https://datasaur.ai/sitemap.xml