# ── Search engine crawlers ────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

# ── AI / LLM crawlers ─────────────────────────────────────────────

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

User-agent: anthropic-ai
Allow: /

# OpenAI – ChatGPT / GPT training / SearchGPT
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# DeepSeek
User-agent: DeepSeekBot
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

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

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

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (used by many LLM training datasets)
User-agent: CCBot
Allow: /

# Bytespider / Bytedance (used for AI training)
User-agent: Bytespider
Allow: /

# ── Social / rich-preview crawlers ───────────────────────────────
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

# ── Catch-all: allow everything not listed above ──────────────────
User-agent: *
Allow: /

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

# llms.txt for AI and LLM crawlers
# https://www.vanakkamdsa.com/llms.txt