# robots.txt — https://siaf.ia.br/
# Formato: RFC 9309 (Robots Exclusion Protocol)
# Política: acesso total para buscadores tradicionais e para crawlers de IA
# generativa. A citabilidade por IA (GEO) é o diferencial de negócio da SIAF,
# portanto os agentes de LLM são explicitamente permitidos.

# --- Regra padrão: todos os user-agents ---
User-agent: *
Allow: /

# --- OpenAI (ChatGPT) ---
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
Allow: /

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

# --- Google (IA generativa: Gemini e AI Overviews) ---
User-agent: Google-Extended
User-agent: GoogleOther
Allow: /

# --- Perplexity ---
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /

# --- Microsoft (Bing e Copilot) ---
User-agent: bingbot
User-agent: msnbot
Allow: /

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

# --- Meta (Llama e AI de la Meta) ---
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
Allow: /

# --- Common Crawl (corpus usado no treinamento de vários LLMs) ---
User-agent: CCBot
Allow: /

# --- Outros agentes de IA e busca ---
User-agent: Amazonbot
User-agent: Bytespider
User-agent: DuckAssistBot
User-agent: cohere-ai
User-agent: MistralAI-User
Allow: /

Sitemap: https://siaf.ia.br/sitemap.xml