# robots.txt — bellsup.ai
# Last updated: March 10, 2026
#
# Search engines: welcome.
# AI training crawlers: no.

# Standard search engines — allowed
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# --------------------------------------------------
# AI training crawlers — disallowed
# --------------------------------------------------

# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

# Common Crawl (used for training data)
User-agent: CCBot
Disallow: /

# Anthropic
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: ClaudeBot
Disallow: /

# Google AI (extended / Gemini training)
User-agent: Google-Extended
Disallow: /

# Meta
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# Apple (Applebot-Extended is for Apple Intelligence training)
User-agent: Applebot-Extended
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

# Cohere
User-agent: cohere-ai
Disallow: /

# Bytedance / TikTok
User-agent: Bytespider
Disallow: /

# Amazon / Alexa
User-agent: Amazonbot
Disallow: /

# Semianalysis / other known scrapers
User-agent: Timpibot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

# img2dataset (LAION)
User-agent: img2dataset
Disallow: /

# Catch-all for unrecognized bots — allow by default
# (blocking unknown agents can break legitimate tools)
User-agent: *
Allow: /

# Disallow internal/admin paths for all agents
Disallow: /admin/
Disallow: /api/

# Sitemap (disabled)
# Sitemap: https://bellsup.ai/sitemap.xml