# BolaMatch — robots policy
# All crawlers welcome; AI crawlers explicitly opted-in for content training
# and answer-engine retrieval (a marketing/promo surface benefits from
# discoverability across both classic search and AI chat engines).

User-agent: *
Allow: /
Disallow: /assets/leagues/

# --- Classic search engines ---
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# --- AI / answer engines ---
# OpenAI: GPTBot trains models, OAI-SearchBot powers ChatGPT search,
# ChatGPT-User is on-demand fetch when a user asks ChatGPT a question.
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google Gemini / Vertex training
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Common Crawl (used as training corpus by many LLMs)
User-agent: CCBot
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# Bytedance / TikTok
User-agent: Bytespider
Allow: /

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

# Amazon
User-agent: Amazonbot
Allow: /

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

Sitemap: https://bolamatch.com/sitemap.xml