# General crawlers
User-agent: *
Disallow:
Sitemap: https://ltl-blog.pages.dev/sitemap.xml

# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

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

# Anthropic
User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

# Meta
User-agent: FacebookBot
Disallow: /

# Apple
User-agent: Applebot-Extended
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

# Common Crawl (used to train many LLMs)
User-agent: CCBot
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

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

# Bytedance / TikTok
User-agent: Bytespider
Disallow: /

# Diffbot
User-agent: Diffbot
Disallow: /

# ImagesiftBot
User-agent: ImagesiftBot
Disallow: /

# Omgili / Webz.io
User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

# DataForSeo
User-agent: DataForSeoBot
Disallow: /

# AI2 (Allen Institute)
User-agent: ai2-bot
Disallow: /

# Timpibot
User-agent: Timpibot
Disallow: /