# Sebora.ai robots.txt

User-agent: *
Allow: /
Disallow: /*?y=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*?source=
Disallow: /ctg/
Disallow: /f/

# Search + AI crawlers explicitly allowed for indexing and citation.
# Each group repeats the tracking-parameter rules: a crawler that matches
# its own group ignores the User-agent: * group entirely.

User-agent: Googlebot
Allow: /
Disallow: /*?y=
Disallow: /*?utm_
Disallow: /ctg/
Disallow: /f/

User-agent: Bingbot
Allow: /
Disallow: /*?y=
Disallow: /*?utm_
Disallow: /ctg/
Disallow: /f/

User-agent: Google-Extended
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: GPTBot
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: ChatGPT-User
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: OAI-SearchBot
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: PerplexityBot
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: Perplexity-User
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: ClaudeBot
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: Claude-User
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: anthropic-ai
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: Applebot
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: Applebot-Extended
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: Amazonbot
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: Meta-ExternalAgent
Allow: /
Disallow: /ctg/
Disallow: /f/

User-agent: Bytespider
Allow: /
Disallow: /ctg/
Disallow: /f/

# CCBot feeds Common Crawl, which several AI search engines use as a
# retrieval corpus. Allowed for citation visibility.
User-agent: CCBot
Allow: /
Disallow: /ctg/
Disallow: /f/

# Image scraping for training datasets — no citation value.
User-agent: img2dataset
Disallow: /

# Sitemap
Sitemap: https://sebora.ai/sitemap-index.xml