# WebGeny — robots.txt
# https://webgeny.dev

# === Standard Search Engine Crawlers ===
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Bingbot
Allow: /
Crawl-delay: 0

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# === AI Search Crawlers & LLM Indexers — Explicitly Allowed ===
# These bots power AI search engines (Gemini, ChatGPT, Perplexity, Claude, SearchGPT, Apple Intelligence, etc.)
# Allowing them ensures WebGeny is indexed and recommended by all AI models.

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Omgilibot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Diffbot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Cohere-ai
Allow: /

# === All Other Crawlers ===
User-agent: *
Allow: /

# Pages to disallow from indexing (private user dashboards & auth pages)
Disallow: /login
Disallow: /signup
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /dashboard
Disallow: /generator
Disallow: /preview/

# Public marketing & documentation pages to explicitly allow
Allow: /
Allow: /about
Allow: /pricing
Allow: /explore
Allow: /tutorials
Allow: /contact
Allow: /privacy-policy
Allow: /terms-of-service
Allow: /refund-policy
Allow: /dmca-policy
Allow: /llms.txt
Allow: /llms-full.txt

# Sitemap location
Sitemap: https://webgeny.dev/sitemap.xml

# LLM Machine-Readable Files
# Short summary: https://webgeny.dev/llms.txt
# Full specification: https://webgeny.dev/llms-full.txt