# robots.txt — HostGrade.pl # Last updated: 2026-04-17 # AI crawlers are explicitly ALLOWED for GEO (Generative Engine Optimisation) # ----------------------------------------------------------------- # Default: all crawlers # ----------------------------------------------------------------- User-agent: * Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # Content usage preferences (draft-romm-aipref-contentsignals) are now # served via the X-Content-Signal HTTP response header on every page — # Google PSI's strict RFC 9309 parser flagged the in-robots directive as # "Unknown", even though content-signal-aware crawlers (Cloudflare, OpenAI) # accept both channels. # ----------------------------------------------------------------- # OpenAI (ChatGPT / GPT-4o training + browsing) # ----------------------------------------------------------------- User-agent: GPTBot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ User-agent: ChatGPT-User Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ User-agent: OAI-SearchBot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Anthropic (Claude) # ----------------------------------------------------------------- User-agent: ClaudeBot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ User-agent: anthropic-ai Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ User-agent: Claude-Web Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Perplexity AI # ----------------------------------------------------------------- User-agent: PerplexityBot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Google (Gemini training + extended AI) # ----------------------------------------------------------------- User-agent: Google-Extended Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Apple (Siri, Apple Intelligence) # ----------------------------------------------------------------- User-agent: Applebot-Extended Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Common Crawl (LLM training datasets) # ----------------------------------------------------------------- User-agent: CCBot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Cohere AI # ----------------------------------------------------------------- User-agent: cohere-ai Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Amazon (Alexa AI / Bedrock) # ----------------------------------------------------------------- User-agent: Amazonbot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # ByteDance (TikTok AI / Doubao) # ----------------------------------------------------------------- User-agent: Bytespider Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Diffbot (structured web intelligence) # ----------------------------------------------------------------- User-agent: Diffbot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Timpi (decentralised AI index) # ----------------------------------------------------------------- User-agent: Timpibot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Omgili / Omgilibot (media intelligence) # ----------------------------------------------------------------- User-agent: Omgili Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ User-agent: Omgilibot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Google (standard web index — explicit for clarity) # ----------------------------------------------------------------- User-agent: Googlebot Allow: / Disallow: /api/ Disallow: /out/ Disallow: /cdn-cgi/ Disallow: /_astro/ # ----------------------------------------------------------------- # Sitemap index + individual sitemaps # ----------------------------------------------------------------- Sitemap: https://hostgrade.pl/sitemap-index.xml Sitemap: https://hostgrade.pl/sitemap-pages.xml Sitemap: https://hostgrade.pl/sitemap-providers.xml Sitemap: https://hostgrade.pl/sitemap-knowledge.xml