# Checkpoint64 — robots.txt
# Allow all well-behaved crawlers and AI assistants. Keep PR previews out of the index.

User-agent: *
Allow: /
Disallow: /pr-preview/

# ---------- AI / LLM crawlers (explicitly welcomed) ----------
# OpenAI — training & GPT model improvement
User-agent: GPTBot
Allow: /

# OpenAI — when a user asks ChatGPT to browse a link
User-agent: ChatGPT-User
Allow: /

# OpenAI — SearchGPT index crawler
User-agent: OAI-SearchBot
Allow: /

# Anthropic — Claude crawler (training/index)
User-agent: ClaudeBot
Allow: /

# Anthropic — legacy identifier
User-agent: anthropic-ai
Allow: /

# Anthropic — when a Claude user clicks a link / asks for a fetch
User-agent: Claude-User
Allow: /

# Anthropic — Claude search index
User-agent: Claude-SearchBot
Allow: /

# Anthropic — legacy web fetcher
User-agent: Claude-Web
Allow: /

# Google — controls inclusion in Bard / Gemini / Vertex AI grounding
User-agent: Google-Extended
Allow: /

# Perplexity — search index
User-agent: PerplexityBot
Allow: /

# Perplexity — on-demand user fetches
User-agent: Perplexity-User
Allow: /

# Apple — Apple Intelligence / Siri grounding
User-agent: Applebot-Extended
Allow: /

# Meta — Llama training crawler
User-agent: meta-externalagent
Allow: /

# Meta — Llama / search
User-agent: FacebookBot
Allow: /

# DuckDuckGo — DuckAssist
User-agent: DuckAssistBot
Allow: /

# Common Crawl — feeds many open-source LLMs
User-agent: CCBot
Allow: /

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

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

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

# Diffbot (used by some AI products for live retrieval)
User-agent: Diffbot
Allow: /

# Amazon — Alexa / Bedrock training crawler
User-agent: Amazonbot
Allow: /

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

# ---------- Known SEO/marketing scrapers (politely blocked) ----------
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

Sitemap: https://checkpoint64.com/sitemap.xml
Host: https://checkpoint64.com