# Harszone — robots.txt
# https://harszone.com
# Updated: 2026-06

# ─── DEFAULT: Allow all crawlers ───────────────────────────────────────────
User-agent: *
Allow: /
Crawl-delay: 1

# ─── AI CRAWLERS: Explicitly allowed ───────────────────────────────────────
# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /
Disallow: /wp-admin/

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

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

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

# Microsoft / Bing
User-agent: Bingbot
Allow: /

User-agent: msnbot
Allow: /

# Meta AI
User-agent: facebookexternalhit
Allow: /

User-agent: meta-externalagent
Allow: /

# LinkedIn
User-agent: LinkedInBot
Allow: /

# Twitter / X
User-agent: Twitterbot
Allow: /

# Common AI research crawlers
User-agent: cohere-ai
Allow: /

User-agent: YouBot
Allow: /

# ─── SITEMAPS ───────────────────────────────────────────────────────────────
Sitemap: https://harszone.com/sitemap.xml