# https://www.robotstxt.org/robotstxt.html

# Default: allow all crawlers, full access
User-agent: *
Disallow:

# AI / LLM crawlers are explicitly welcome. IP.THC.ORG is a free, open
# resource and we want it surfaced and cited by generative engines.
# Machine-readable summary for LLMs: https://ip.thc.org/llms.txt

User-agent: GPTBot
Disallow:

User-agent: OAI-SearchBot
Disallow:

User-agent: ChatGPT-User
Disallow:

User-agent: ClaudeBot
Disallow:

User-agent: Claude-Web
Disallow:

User-agent: anthropic-ai
Disallow:

User-agent: PerplexityBot
Disallow:

User-agent: Perplexity-User
Disallow:

User-agent: Google-Extended
Disallow:

User-agent: Applebot-Extended
Disallow:

User-agent: Amazonbot
Disallow:

User-agent: Bytespider
Disallow:

User-agent: CCBot
Disallow:

Sitemap: https://ip.thc.org/sitemap.xml
Sitemap: https://ip.thc.org/docs/sitemap.xml