# Giggli Labs — robots.txt
# Public marketing site. AI crawlers are explicitly welcome.

User-agent: *
Allow: /

# === LLM training & answer-engine crawlers ===
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Diffbot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: YouBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: ImagesiftBot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Googlebot
Allow: /

# Block low-value scrapers that hammer marketing sites
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

Sitemap: https://giggli.ca/sitemap.xml