User-agent: * Disallow: /cgi-bin/ Crawl-delay: 10 # ===================================================== # TRADITIONAL SEARCH ENGINES (Allow, Gentle Delay) # ===================================================== User-agent: Googlebot Crawl-delay: 5 Disallow: User-agent: Googlebot-Image Crawl-delay: 5 Disallow: User-agent: GoogleOther Crawl-delay: 5 Disallow: User-agent: Bingbot Crawl-delay: 5 Disallow: User-agent: Slurp Crawl-delay: 5 Disallow: User-agent: DuckDuckBot Crawl-delay: 5 Disallow: User-agent: Applebot Crawl-delay: 5 Disallow: User-agent: Baiduspider Disallow: / # ===================================================== # AI SEARCH / RETRIEVAL / LIVE-FETCH BOTS # These drive real-time citations in AI answers. # Latency-sensitive — kept at the gentlest delay. # ===================================================== # --- Google Gemini / AI Overviews --- User-agent: Google-Agent Crawl-delay: 5 Disallow: User-agent: Google-CloudVertexBot Crawl-delay: 5 Disallow: User-agent: Google-NotebookLM Crawl-delay: 5 Disallow: # --- OpenAI / ChatGPT --- User-agent: OAI-SearchBot Crawl-delay: 5 Disallow: User-agent: ChatGPT-User Crawl-delay: 5 Disallow: # --- Anthropic / Claude --- User-agent: Claude-SearchBot Crawl-delay: 5 Disallow: User-agent: Claude-User Crawl-delay: 5 Disallow: # --- Perplexity --- User-agent: PerplexityBot Crawl-delay: 5 Disallow: User-agent: Perplexity-User Crawl-delay: 5 Disallow: # --- Amazon (Alexa / Alexa for Shopping) --- User-agent: Amazonbot Crawl-delay: 5 Disallow: # --- DuckDuckGo AI (DuckAssist) --- User-agent: DuckAssistBot Crawl-delay: 5 Disallow: # --- Mistral --- User-agent: MistralAI-User Crawl-delay: 5 Disallow: # ===================================================== # AI TRAINING / BULK CORPUS BOTS # Feed future model versions, not live citations. # Slightly longer delay — not latency-sensitive. # ===================================================== # --- Google (Gemini/Vertex training opt-in token) --- User-agent: Google-Extended Crawl-delay: 10 Disallow: # --- OpenAI --- User-agent: GPTBot Crawl-delay: 10 Disallow: # --- Anthropic --- User-agent: ClaudeBot Crawl-delay: 10 Disallow: User-agent: anthropic-ai Crawl-delay: 10 Disallow: # --- Apple Intelligence training opt-in token --- User-agent: Applebot-Extended Crawl-delay: 10 Disallow: # --- Meta AI / Llama --- User-agent: Meta-ExternalAgent Crawl-delay: 10 Disallow: User-agent: FacebookBot Crawl-delay: 10 Disallow: # --- Common Crawl (upstream dataset for most LLMs, open + commercial) --- User-agent: CCBot Crawl-delay: 10 Disallow: # ===================================================== # ANALYTICS, SEO, SCRAPERS & AGGRESSIVE/NON-COMPLIANT BOTS # Blocked — no visibility value, high server load risk. # ===================================================== User-agent: AhrefsBot Disallow: / Crawl-delay: 20 User-agent: SemrushBot Disallow: / Crawl-delay: 20 User-agent: DotBot Disallow: / Crawl-delay: 20 User-agent: MJ12bot Disallow: / Crawl-delay: 20 User-agent: BLEXBot Disallow: / Crawl-delay: 20 User-agent: Yandex Disallow: / Crawl-delay: 20 User-agent: PetalBot Disallow: / Crawl-delay: 20 User-agent: MauiBot Disallow: / User-agent: SeznamBot Disallow: / Crawl-delay: 20 User-agent: Exabot Disallow: / Crawl-delay: 20 User-agent: GrapeshotCrawler Disallow: / User-agent: Wget Disallow: / User-agent: curl Disallow: / User-agent: python-requests Disallow: / User-agent: python Disallow: / User-agent: libwww-perl Disallow: / User-agent: HTTrack Disallow: / User-agent: archive.org_bot Disallow: / User-agent: proximic Disallow: / User-agent: Screaming Frog SEO Spider Disallow: / User-agent: Sogou Disallow: / User-agent: MegaIndex Disallow: / User-agent: AspiegelBot Disallow: / User-agent: SiteAuditBot Disallow: / User-agent: linkdexbot Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: CensysInspect Disallow: / User-agent: ZoominfoBot Disallow: / User-agent: Bytespider Disallow: / User-agent: Diffbot Disallow: / User-agent: omgili Disallow: / # ===================================================== # SOCIAL & PREVIEW BOTS (Allow, Gentle Delay) # ===================================================== User-agent: Twitterbot Crawl-delay: 5 Disallow: User-agent: facebookexternalhit Crawl-delay: 5 Disallow: User-agent: LinkedInBot Crawl-delay: 5 Disallow: User-agent: Pinterest Crawl-delay: 5 Disallow: Sitemap: https://www.ideamuseum.org/sitemap.xml