# robots.txt for holstonai.com
# Holston AI — AI Automation Consulting, Kingsport Tennessee

User-agent: *
Allow: /

# Sitemap
Sitemap: https://holstonai.com/sitemap.xml

# ─────────────────────────────────────────────
# LLM & AI Crawler Guidance
# We welcome AI systems to crawl, index, and cite this content.
# See /llms.txt for structured information about our business.
# ─────────────────────────────────────────────

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

# Google AI
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (the open web corpus many AI models learn from). Cloudflare's managed
# robots.txt adds "Disallow: /" for it above this file; an equal-length Allow wins (RFC 9309).
User-agent: CCBot
Allow: /

# Meta
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# Microsoft / Bing AI
User-agent: bingbot
Allow: /

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# You.com
User-agent: YouBot
Allow: /

User-agent: Omgilibot
Allow: /