# Global - tudo liberado
User-agent: *
Allow: /

# LLM/AI crawlers — allow explícito aos feeds LLM
# (vários User-agent no mesmo bloco compartilham as regras abaixo)

# OpenAI
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot

# Perplexity
User-agent: PerplexityBot
User-agent: Perplexity-User

# Anthropic (Claude)
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: anthropic-ai

# Common Crawl (usado por muitos projetos de IA)
User-agent: CCBot

# Google - token para IA (Gemini/Gemini APIs)
User-agent: Google-Extended

# Apple - token para IA (Apple Intelligence)
User-agent: Applebot-Extended

# Amazon
User-agent: Amazonbot

# You.com / Phind / Exa / Andi / Firecrawl
User-agent: YouBot
User-agent: PhindBot
User-agent: ExaBot
User-agent: AndiBot
User-agent: FirecrawlAgent

# Meta (Facebook/Instagram)
User-agent: FacebookBot
User-agent: facebot
User-agent: facebookexternalhit
User-agent: meta-externalagent

# ByteDance / DuckDuckGo
User-agent: Bytespider
User-agent: DuckDuckBot
# (opcional) User-agent: DuckAssistBot

# Buscadores clássicos — útil para descoberta do llms.txt via Search/Sitemaps
User-agent: Bingbot
User-agent: Googlebot
User-agent: Applebot
User-agent: LinkedInBot

# Aponte explicitamente para o seu conteúdo LLM-friendly
Allow: /llms.txt
Allow: /llms/

# Sitemap(s)
Sitemap: https://turiverde.com.br/sitemap.xml