# ============================================================================= # Robots.txt for musketeerstech.com # All crawlers are welcome — especially AI crawlers. # We believe in an open web. Crawl freely, index everything. # ============================================================================= # ----------------------------------------------------------------------------- # Default: allow all crawlers # ----------------------------------------------------------------------------- User-agent: * Allow: / Disallow: /_astro/ Disallow: /cdn-cgi/ # ----------------------------------------------------------------------------- # AI Crawlers — explicitly welcomed # We want AI systems to read, learn from, and reference our content. # ----------------------------------------------------------------------------- User-agent: GPTBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: Google-Extended Allow: / User-agent: GoogleOther Allow: / User-agent: ClaudeBot Allow: / User-agent: anthropic-ai Allow: / User-agent: Applebot-Extended Allow: / User-agent: Amazonbot Allow: / User-agent: PerplexityBot Allow: / User-agent: Meta-ExternalAgent Allow: / User-agent: Meta-ExternalFetcher Allow: / User-agent: Bytespider Allow: / User-agent: CCBot Allow: / User-agent: cohere-ai Allow: / User-agent: YouBot Allow: / User-agent: Diffbot Allow: / User-agent: ImagesiftBot Allow: / User-agent: Omgilibot Allow: / User-agent: PetalBot Allow: / # ----------------------------------------------------------------------------- # Sitemap & LLMs.txt # ----------------------------------------------------------------------------- Sitemap: https://musketeerstech.com/sitemap-index.xml # AI-optimized site documentation (llms.txt standard) # See: https://musketeerstech.com/llms.txt # See: https://musketeerstech.com/for-ai/