# Parrot — robots.txt
# Updated: 2026-08-28
#
# Open to all crawlers, including AI / LLM crawlers. Per-crawler Allow
# blocks below are redundant with the default User-agent: * Allow: /
# rule but make our intent explicit and survive future tightening of
# the default policy. If you ever want to opt out of one of these,
# change its Allow: / to Disallow: /.

User-agent: *
Allow: /
Disallow: /cms

# OpenAI (ChatGPT browsing + training)
User-agent: GPTBot
Allow: /
Disallow: /cms

User-agent: ChatGPT-User
Allow: /
Disallow: /cms

User-agent: OAI-SearchBot
Allow: /
Disallow: /cms

# Anthropic (Claude browsing + training)
User-agent: ClaudeBot
Allow: /
Disallow: /cms

User-agent: anthropic-ai
Allow: /
Disallow: /cms

User-agent: Claude-Web
Allow: /
Disallow: /cms

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /cms

User-agent: Perplexity-User
Allow: /
Disallow: /cms

# Google AI (separate from Googlebot; controls inclusion in AI Overviews
# / Vertex AI training). Allow ON, since we want to be cited.
User-agent: Google-Extended
Allow: /
Disallow: /cms

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

# Meta AI
User-agent: FacebookBot
Allow: /
Disallow: /cms

User-agent: Meta-ExternalAgent
Allow: /
Disallow: /cms

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
Disallow: /cms

# Bytedance
User-agent: Bytespider
Allow: /
Disallow: /cms

# Diffbot, You.com, Cohere, Mistral and other knowledge-graph crawlers
User-agent: DiffbotBot
Allow: /
Disallow: /cms

User-agent: YouBot
Allow: /
Disallow: /cms

User-agent: cohere-ai
Allow: /
Disallow: /cms

User-agent: MistralAI-User
Allow: /
Disallow: /cms

Sitemap: https://www.parrotapp.com/sitemap.xml
Sitemap: https://www.parrotapp.com/sitemap-french.xml