# robots.txt for UrbaHive
# Updated: 2026-05-02

# Default — allow all crawlers
User-agent: *
Allow: /

# Search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Bingbot
Allow: /
Crawl-delay: 0

# AI / LLM crawlers — explicit opt-in
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

# Social media crawlers
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# Sitemap location
Sitemap: https://www.urbahive.com/sitemap.xml

# LLM-friendly corpus
# https://www.urbahive.com/llms.txt
# https://www.urbahive.com/llms-full.txt

# Host preference (helps with www vs non-www)
Host: https://www.urbahive.com