# https://mymemory.dev/robots.txt
#
# Search engines and AI search/assistant crawlers are welcome on public pages:
# landing, pricing, integrations, extension, legal, and /llms.txt. AI training
# crawlers are not (Cloudflare AI Crawl Control blocks the same ones at the edge).
#
# Two groups on purpose. A crawler obeys only the most specific group that
# names it, so every welcome agent shares ONE group (a separate group for a
# bot would silently drop the Disallow rules at the bottom for that bot).
#
# robots.txt is advisory. Private surfaces are protected by auth and send
# `noindex` via buildNoIndexMeta; these rules only save crawl budget.

# AI training crawlers and training opt-out tokens: not allowed.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: CCBot
User-agent: Bytespider
User-agent: PetalBot
Disallow: /

# Search engines, AI search indexes and user-initiated AI fetches: welcome.
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckDuckBot
User-agent: Baiduspider
User-agent: Sogou web spider
User-agent: 360Spider
# OpenAI: ChatGPT search index and user-initiated fetches
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
# Anthropic: Claude search index and user-initiated fetches
User-agent: Claude-SearchBot
User-agent: Claude-User
# Perplexity: index and user-initiated fetches
User-agent: PerplexityBot
User-agent: Perplexity-User
# Other AI assistants
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: *
# Content Signals (contentsignals.org): search indexing and AI answers are
# permitted, AI training is not.
# Keep in sync with CONTENT_SIGNAL in app/lib/agent-discovery.ts.
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Allow: /llms.txt
Allow: /openapi.json
Allow: /.well-known/api-catalog
Allow: /integrations/
Allow: /pricing
Allow: /extension
Allow: /shortcut
Allow: /open-source

# Private app surfaces (authenticated user data)
Disallow: /dashboard
Disallow: /vault
Disallow: /home
Disallow: /chat
Disallow: /editor
Disallow: /notes/
Disallow: /content
Disallow: /space/
Disallow: /onboarding
Disallow: /admin

# Auth, billing, and transactional endpoints
Disallow: /signin
Disallow: /callback
Disallow: /auth
Disallow: /pay
Disallow: /action
Disallow: /backend/
Disallow: /metrics

# Main site, docs (changelog = release notes), API host and blog. The API reference and its
# llms.txt live on docs.mymemory.dev.
Sitemap: https://mymemory.dev/sitemap.xml
Sitemap: https://docs.mymemory.dev/sitemap.xml
Sitemap: https://api.mymemory.dev/sitemap.xml