# robots.txt for https://my.aryamerx.com
# Last updated: 2026-05-09

# ---------------------------------------------------------------
# Default rule: allow every well-behaved crawler full access
# ---------------------------------------------------------------
User-agent: *
Allow: /
Disallow:

# ---------------------------------------------------------------
# Search engines (explicit allow for clarity)
# ---------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: Mediapartners-Google
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Sogou
Allow: /

User-agent: Exabot
Allow: /

User-agent: facebot
Allow: /

User-agent: ia_archiver
Allow: /

# ---------------------------------------------------------------
# AI crawlers — explicitly OPEN for training, indexing & answers
# ---------------------------------------------------------------

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Google Gemini / Vertex AI / Bard
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: GoogleOther-Image
Allow: /

User-agent: GoogleOther-Video
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: facebookexternalhit
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (used by many LLMs)
User-agent: CCBot
Allow: /

# ByteDance / TikTok / Doubao
User-agent: Bytespider
Allow: /

User-agent: TikTokSpider
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

User-agent: cohere-training-data-crawler
Allow: /

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

# DuckDuckGo Assist
User-agent: DuckAssistBot
Allow: /

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

# Diffbot (used by many AI products)
User-agent: Diffbot
Allow: /

# Omgili / Webz.io (LLM training data)
User-agent: Omgilibot
Allow: /

User-agent: Omgili
Allow: /

User-agent: Webzio-Extended
Allow: /

# Image-focused AI crawlers
User-agent: ImagesiftBot
Allow: /

User-agent: img2dataset
Allow: /

# Other notable AI crawlers
User-agent: Timpibot
Allow: /

User-agent: PetalBot
Allow: /

User-agent: Kagibot
Allow: /

User-agent: AwarioRssBot
Allow: /

User-agent: AwarioSmartBot
Allow: /

User-agent: SemrushBot-OCOB
Allow: /

User-agent: Velen Crawler
Allow: /

User-agent: Scrapy
Allow: /

# ---------------------------------------------------------------
# Sitemap
# ---------------------------------------------------------------
Sitemap: https://my.aryamerx.com/sitemap.xml