# robots.txt — Stripe Projects
# Public site pages may be crawled, indexed, and used to train AI models.
# Dynamic stack share URLs (/s/) are generated links, not canonical pages, so
# they stay out of every group below.
#
# Content-Signal (contentsignals.org) states the same policy in machine-readable
# form: search=yes, ai-input=yes (RAG / live retrieval), ai-train=yes (model
# training).

User-agent: *
Allow: /
Allow: /.well-known/
Allow: /developers/
Allow: /docs/api/
Allow: /llms.txt
Allow: /skill.md
Allow: /auth.md
Allow: /index.html.md
Allow: /404.md
Allow: /api/openapi.json
Allow: /sitemap.xml
Disallow: /s/
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Training crawlers and training-usage tokens — allowed. Listed explicitly so
# the opt-in is unambiguous to operators that look for their own user-agent
# rather than falling back to the wildcard group.
User-agent: GPTBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: cohere-ai
User-agent: meta-externalagent
User-agent: CCBot
Allow: /
Disallow: /s/
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Retrieval and assistant crawlers — allowed (unchanged).
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-Web
User-agent: PerplexityBot
Allow: /
Disallow: /s/
Content-Signal: ai-train=yes, search=yes, ai-input=yes

Sitemap: https://projects.dev/sitemap.xml