# HelioLink Technologies LLC
# https://heliolink.net
# Last Updated: 2025-12-27

# ===========================================
# TRADITIONAL SEARCH ENGINES
# ===========================================

User-agent: Googlebot
Allow: /

User-agent: bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

# ===========================================
# OPENAI (ChatGPT, ChatGPT Search)
# ===========================================

# Training data for future models
User-agent: GPTBot
Allow: /

# Search indexing (NOT training) - powers ChatGPT Search
User-agent: OAI-SearchBot
Allow: /

# Real-time browsing on user request
User-agent: ChatGPT-User
Allow: /

# ===========================================
# GOOGLE AI (Gemini, AI Overviews)
# ===========================================

# Controls AI training while Googlebot handles search
User-agent: Google-Extended
Allow: /

# ===========================================
# ANTHROPIC (Claude)
# ===========================================

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

# ===========================================
# PERPLEXITY AI
# ===========================================

# Search indexing
User-agent: PerplexityBot
Allow: /

# Real-time fetching
User-agent: Perplexity-User
Allow: /

# ===========================================
# APPLE (Siri, Apple Intelligence)
# ===========================================

User-agent: Applebot
Allow: /

# AI Training (WWDC 2024)
User-agent: Applebot-Extended
Allow: /

# ===========================================
# AMAZON (Alexa, Rufus)
# ===========================================

# General AI training
User-agent: Amazonbot
Allow: /

# Search-only (Alexa, Rufus)
User-agent: Amzn-SearchBot
Allow: /

# Real-time queries
User-agent: Amzn-User
Allow: /

# ===========================================
# META (Meta AI, Llama)
# ===========================================

# AI training (Llama)
User-agent: meta-externalagent
Allow: /

# Real-time RAG fetching
User-agent: meta-externalfetcher
Allow: /

# Link previews
User-agent: facebookexternalhit
Allow: /

# ===========================================
# OTHER AI PLATFORMS
# ===========================================

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

# Common Crawl (training data source)
User-agent: CCBot
Allow: /

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

# ByteDance
User-agent: Bytespider
Allow: /

# ===========================================
# DEFAULT & SITEMAP
# ===========================================

User-agent: *
Allow: /

Sitemap: https://heliolink.net/sitemap.xml