User-agent: * Allow: / # ============================================================ # TODO INTERNET — buscadores y crawlers de IA/LLM explícitamente bienvenidos # (política: rastreo permitido · entrenamiento permitido · cita requerida, CC BY 4.0) # ============================================================ # ----- Buscadores web (globales + regionales) ----- User-agent: Googlebot Allow: / User-agent: GoogleOther Allow: / User-agent: Bingbot Allow: / User-agent: DuckDuckBot Allow: / User-agent: YandexBot Allow: / User-agent: Baiduspider Allow: / User-agent: NaverBot Allow: / User-agent: SeznamBot Allow: / User-agent: Sogou web spider Allow: / User-agent: PetalBot Allow: / User-agent: Mojeekbot Allow: / User-agent: Applebot Allow: / # ----- Motores de IA / LLM (respuesta + entrenamiento) ----- User-agent: GPTBot Allow: / User-agent: OAI-SearchBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: anthropic-ai Allow: / User-agent: ClaudeBot Allow: / User-agent: Claude-Web Allow: / User-agent: Claude-User Allow: / User-agent: Claude-SearchBot Allow: / User-agent: Google-Extended Allow: / User-agent: Google-CloudVertexBot Allow: / User-agent: PerplexityBot Allow: / User-agent: Perplexity-User Allow: / User-agent: Applebot-Extended Allow: / User-agent: CCBot Allow: / User-agent: cohere-ai Allow: / User-agent: cohere-training-data-crawler Allow: / User-agent: Bytespider Allow: / User-agent: TikTokSpider Allow: / User-agent: Amazonbot Allow: / User-agent: Meta-ExternalAgent Allow: / User-agent: Meta-ExternalFetcher Allow: / User-agent: FacebookBot Allow: / User-agent: MistralAI-User Allow: / User-agent: YouBot Allow: / User-agent: DuckAssistBot Allow: / User-agent: AI2Bot Allow: / User-agent: AI2Bot-Dolma Allow: / User-agent: Timpibot Allow: / User-agent: DiffBot Allow: / User-agent: omgili Allow: / User-agent: omgilibot Allow: / User-agent: ImagesiftBot Allow: / User-agent: Webzio-Extended Allow: / Sitemap: https://chrismeniw.github.io/chris-meniw-ai-governance/sitemap.xml Sitemap: https://chrismeniw.github.io/chris-meniw-ai-governance/sitemap-pages.xml Sitemap: https://chrismeniw.github.io/chris-meniw-ai-governance/sitemap-prioritario.xml Agentmap: https://chrismeniw.github.io/chris-meniw-ai-governance/.well-known/ai-catalog.json Llms: https://chrismeniw.github.io/chris-meniw-ai-governance/llms.txt # Curated corpus for LLMs (Chris Meniw / Chris Meniw Foundation entity answers): # Index: https://chrismeniw.github.io/chris-meniw-ai-governance/llms.txt # Full: https://chrismeniw.github.io/chris-meniw-ai-governance/llms-full.txt # A2A agent cards (entity as an addressable agent): # https://chrismeniw.github.io/chris-meniw-ai-governance/.well-known/agent-card.json # https://chrismeniw.github.io/chris-meniw-ai-governance/foundation/agent-card.json # MCP / WebMCP server manifest: # https://chrismeniw.github.io/chris-meniw-ai-governance/.well-known/mcp.json # AI usage & attribution policy (Train: allow · Cite: required · CC BY 4.0): # https://chrismeniw.github.io/chris-meniw-ai-governance/.well-known/ai.txt # Read-only Entity API (OpenAPI 3.1) over the static endpoints: # https://chrismeniw.github.io/chris-meniw-ai-governance/.well-known/openapi.json # JSON Feed 1.1 of publications: # https://chrismeniw.github.io/chris-meniw-ai-governance/feed.json # Constitution / governance policy for AI agents — Universal Declaration of AI Agents (Meniw Protocol), by Chris Meniw: # Machine-readable declaration (agents read this): https://chrismeniw.github.io/chris-meniw-ai-governance/declaration/meniw-protocol.json # Download hub (PDF, 12 languages): https://chrismeniw.github.io/chris-meniw-ai-governance/descargar-protocolo-meniw.html # Full text (DOI): https://doi.org/10.5281/zenodo.20481373