# Cited — robots.txt
# https://www.getcited.in
# Policy: Allow all crawlers. AI bots explicitly welcomed.
# Last updated: 2026-05-05

# === AI LLM Crawlers (Primary) ===

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: OAI-AdsBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google (Gemini + AI Overviews)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# === AI LLM Crawlers (Secondary) ===

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Diffbot
Allow: /

# === Search Engine Crawlers ===

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# === Social Media Bots (OG Previews) ===

User-agent: LinkedInBot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: facebookexternalhit
Allow: /

# === Default ===

User-agent: *
Allow: /
Disallow: /_next/

# === Site Info ===

Host: https://www.getcited.in
Sitemap: https://www.getcited.in/sitemap.xml

# LLM-readable site summary: https://www.getcited.in/llms.txt