# https://www.robotstxt.org/robotstxt.html
# trashlab.com is public marketing content. Every crawler may read all of it.
# The named groups below are explicit on purpose: some AI crawlers only trust
# a group that names them, and the list documents which bots we want.
User-agent: *
Allow: /

# Search engines. ChatGPT search and Copilot use the Bing index.
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# OpenAI: training, ChatGPT search index, and live fetches for a user.
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic: training, Claude search index, and live fetches for a user.
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity: search index and live fetches for a user.
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google Gemini and Apple Intelligence use these tokens for AI use of content.
User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

# Other AI assistants and the open crawl that many models train on.
User-agent: DuckAssistBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: CCBot
Allow: /

# Sitemap
Sitemap: https://trashlab.com/sitemap.xml