# aimo's AI Articles — Crawler Policy
# Content licensed under CC-BY-4.0
# Author: aimo (艾摸)
# Contact: porsche232323@gmail.com
# Repository: https://github.com/aimo14913/aimo-ai-articles

# Default: welcome all crawlers, full access
User-agent: *
Allow: /

# Sitemap discovery
Sitemap: https://aimo14913.github.io/aimo-ai-articles/sitemap.xml

# AI / LLM crawlers — explicit allow
# These are the user-agents major AI companies use for training / search indexing.
# Listed individually for clarity and to override any platform-level defaults.

# OpenAI (ChatGPT, GPT models)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

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

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Google (Gemini training set)
User-agent: Google-Extended
Allow: /

User-agent: Googlebot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Common Crawl (feeds many LLM training datasets)
User-agent: CCBot
Allow: /

# Meta (Llama)
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# Apple (Apple Intelligence)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# ByteDance (Doubao)
User-agent: Bytespider
Allow: /

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

User-agent: BingPreview
Allow: /

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

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

# DuckAssistBot
User-agent: DuckAssistBot
Allow: /

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

# Diffbot
User-agent: Diffbot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /