# robots.txt for Thai Tai Vietnamese - https://www.thaitaivietnamese.ca

# All crawlers
User-agent: *
Allow: /
Allow: /llms.txt
Noindex: /llms.txt
Disallow: /.github/
Disallow: /.vscode/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# AI crawlers and assistants (allowed to read llms.txt and public pages)
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: cohere-ai
User-agent: meta-externalagent
Allow: /
Allow: /llms.txt
Noindex: /llms.txt
Disallow: /.github/
Disallow: /.vscode/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Google Ads bots (must be named explicitly)
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
Allow: /

# Crawl delay for heavy bots
User-agent: Baiduspider
Crawl-delay: 10

# llms.txt: AI-readable site summary; not intended for search indexing
# LLMs: https://www.thaitaivietnamese.ca/llms.txt

# Sitemap
Sitemap: https://www.thaitaivietnamese.ca/sitemap.xml