# howtogetcitedinai.com — allow every legitimate AI + search crawler
# Verified user-agent strings as of June 2026

# --- OpenAI ---
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: /

User-agent: anthropic-ai
Allow: /

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

User-agent: Perplexity-User
Allow: /

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

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# --- Microsoft / Bing ---
User-agent: Bingbot
Allow: /

User-agent: msnbot
Allow: /

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

User-agent: Applebot-Extended
Allow: /

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

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

User-agent: FacebookBot
Allow: /

# --- Other notable AI/search ---
User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: CCBot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Cohere-ai
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: PetalBot
Allow: /

# --- Default: allow everyone else ---
User-agent: *
Allow: /

# --- Explicit allow: AI answer engines (redundant with per-bot blocks
#     above, kept for scanners that only read a single named block) ---
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Google-Extended
Allow: /

# --- Block: bulk SEO scrapers ---
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

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