# Arahi AI - Robots.txt
# https://arahi.ai/robots.txt
# Updated: 2026-02-18

# Default: Allow all legitimate crawlers
User-agent: *
Allow: /

# Block Next.js internal paths only
Disallow: /api/
Disallow: /_next/
Disallow: /admin/
Disallow: /private/

# Sitemaps
Sitemap: https://arahi.ai/sitemap.xml

# LLM Content Policy
# See https://arahi.ai/llms.txt for structured content for AI systems

# ─── AI Search Engine Crawlers ───
# OpenAI (ChatGPT, GPT search)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic (Claude)
User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Google (Gemini, AI Overviews, SGE)
User-agent: Google-Extended
Allow: /

User-agent: Googlebot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Microsoft (Copilot, Bing AI)
User-agent: Bingbot
Allow: /

User-agent: BingPreview
Allow: /

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

# Brave Search (powers Claude's web search)
User-agent: Brave
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: meta-externalagent
Allow: /

# Apple (Siri, Spotlight)
User-agent: Applebot
Allow: /

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

# Common Crawl (used by many AI training pipelines)
User-agent: CCBot
Allow: /

# ─── SEO Tools - Block aggressive crawlers ───
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /