# Webamon.com Robots.txt
# Updated: January 2025

# Allow all web crawlers to access the site
User-agent: *
Allow: /

# Specific rules for major search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /
Crawl-delay: 2

# AI/LLM Crawlers - Allow access for better AI search visibility
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: CCBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Disallow access to potentially sensitive or unnecessary directories
Disallow: /admin/
Disallow: /private/
Disallow: /temp/
Disallow: /tmp/
Disallow: /cache/
Disallow: /logs/
Disallow: /backup/
Disallow: /config/
Disallow: /.git/
Disallow: /node_modules/
Disallow: /vendor/

# Disallow access to file types that shouldn't be indexed
Disallow: /*.log$
Disallow: /*.sql$
Disallow: /*.gz$
Disallow: /*.tar$
Disallow: /*.zip$
Disallow: /*.bak$

# Allow access to important assets
Allow: /css/
Allow: /js/
Allow: /img/
Allow: /fonts/

# Block access to potentially sensitive files
Disallow: /.htaccess
Disallow: /.htpasswd
Disallow: /wp-config.php
Disallow: /config.php
Disallow: /.env

# LLM.txt files for AI/LLM content discovery
# These files provide structured information for Large Language Models
Allow: /llm.txt
Allow: /llm-full.txt

# Sitemap location (update with your actual sitemap URL when created)
Sitemap: https://webamon.com/sitemap.xml

# Additional sitemaps for different content types
# Sitemap: https://webamon.com/sitemap-pages.xml
# Sitemap: https://webamon.com/sitemap-blog.xml
# Sitemap: https://webamon.com/sitemap-api-docs.xml

# Host declaration (helps with canonicalization)
Host: https://webamon.com