User-agent: *
# Content usage preferences (contentsignals.org / draft-romm-aipref-contentsignals).
# search=yes   -> may build a search index and show results and short excerpts
# ai-input=yes -> may use this content as input for AI answers (RAG, grounding, citations)
# ai-train=no  -> may NOT use this content to train or fine-tune AI models
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /*?s=

# AI crawlers — explicitly welcome to crawl, con las mismas preferencias de uso.
# El Content-Signal se repite en cada grupo porque un crawler que coincide con un
# grupo específico ignora el grupo "*" (RFC 9309). Así el ai-train=no también les llega.
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: meta-externalagent
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# AI context files
Allow: /llms.txt
Allow: /llm-full.txt

Sitemap: https://necode.io/sitemap.xml