# Am Hazak (www.amhazak.com)
# Search engines and AI assistants may read pages and cite them.
# Crawlers that collect training data may not (Content-Signal: ai-train=no).
# Automated bulk extraction of the site, and of the kosher directory in
# particular, is not permitted: https://www.amhazak.com/terms#automated-access

User-agent: *
Allow: /

# Search engines
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Yandex
Allow: /

User-agent: YandexBot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: SeznamBot
Allow: /

User-agent: Yeti
Allow: /

User-agent: Applebot
Allow: /

# AI assistants: retrieval and user-initiated fetches (citation)
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: MistralAI-User
Allow: /

# AI training-data crawlers
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: TikTokSpider
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: Novellum
Disallow: /

User-agent: ProRataInc
Disallow: /

User-agent: Anchor Browser
Disallow: /

Content-Signal: ai-train=no, search=yes, ai-input=yes

Sitemap: https://www.amhazak.com/sitemap.xml