# jupitersense.com — robots.txt
# Last updated: 2026-04-17

# ─── Default rules for all crawlers ────────────────────────
User-agent: *
Allow: /
# Private license-management console — keep out of all indexes.
Disallow: /admin/

# Note: /legal/refund.html is crawlable but deprioritised via internal
# linking — refund-facing SEO content lives in /faq.html.

# ─── Explicit allow for AI crawlers ────────────────────────
# We WANT to be cited by these. Allow them everywhere.

# OpenAI (ChatGPT, ChatGPT Search)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google (Gemini, Search Generative Experience)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# Microsoft (Copilot, Bing Chat)
User-agent: Bingbot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Apple (Apple Intelligence)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (feeds many open-source models)
User-agent: CCBot
Allow: /

# Meta (Llama training)
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# Amazon (Alexa, Q)
User-agent: Amazonbot
Allow: /

# DuckDuckGo
User-agent: DuckAssistBot
Allow: /

# You.com
User-agent: YouBot
Allow: /

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

# Mistral
User-agent: MistralAI-User
Allow: /

# ─── Sitemap ───────────────────────────────────────────────
Sitemap: https://jupitersense.com/sitemap.xml