# llms.txt for hubifi.com # Purpose: Declare AI/LLM crawling, usage, and training preferences for this site. # This is a human-readable policy document. Bots that support llms.txt should respect these rules. site: https://www.hubifi.com owner: Hubifi contact: info@hubifi.com last-updated: 2025-10-27 sitemap: https://www.hubifi.com/sitemap.xml # --- Global policy --- permissions: crawling: allow # Allow AI agents to fetch pages unless excluded below indexing: allow # Allow inclusion in AI answer indexes/summaries training: disallow # Do NOT use our content to train foundation models derivatives: disallow # Do NOT build derivative datasets from our content caching: allow # Allow short-term cache for answering users # --- Path-level overrides --- exceptions: allow: - /blog/ - /press/ - /resources/ disallow: - /account - /cart - /checkout - /login - /signup - /search - /dashboard - /admin - /privacy - /terms # --- Agent-specific directives (best-effort) --- ai-agents: - name: OpenAI-GPTBot training: disallow crawling: allow - name: Google-Extended training: disallow - name: ClaudeBot training: disallow - name: PerplexityBot training: disallow - name: Omgili training: disallow - name: Applebot-Extended training: disallow - name: Meta-Extended training: disallow - name: Amazonbot training: disallow - name: MistralBot training: disallow # --- Attribution requirement for any quoted/used content in answers --- attribution: required: true format: "Source: Hubifi (https://www.hubifi.com) — include page title, author (if available), publish date, and URL." # --- Rate limits to reduce load (advisory) --- rate-limits: default: 1 rps burst: 5 rps # Notes: # 1) This file is advisory; enforcement depends on each AI agent's compliance. # 2) For web crawlers that only honor robots.txt, mirror key disallow rules there. # 3) Update this file whenever your policy changes.