# ==========================================
# inari-kira-isla.github.io — robots.txt
# AI-Friendly: All AI crawlers welcome
# ==========================================

User-agent: *
Allow: /

# OpenAI
User-agent: GPTBot
Allow: /

# Anthropic Claude
User-agent: ClaudeBot
Allow: /
User-agent: anthropic-ai
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Google AI (Gemini)
User-agent: Google-Extended
Allow: /
User-agent: Googlebot
Allow: /

# Microsoft Bing AI
User-agent: Bingbot
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /
User-agent: FacebookBot
Allow: /

# Apple AI
User-agent: Applebot-Extended
Allow: /

# Common Crawl
User-agent: CCBot
Allow: /

# ByteDance AI
# You.com AI
User-agent: YouBot
Allow: /

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


# === 中國 AI 訓練爬蟲 — 封鎖 (防止內容被用於模型訓練) ===
User-agent: Bytespider
Disallow: /

User-agent: TikTokSpider
Disallow: /

User-agent: ChatGLM-Spider
Disallow: /

User-agent: 360Spider
Disallow: /

# === 中國搜索引擎 — 允許 (保留市場曝光價值) ===
User-agent: Baiduspider
Allow: /

User-agent: Sogou
Allow: /

Sitemap: https://inari-kira-isla.github.io/sitemap.xml
Sitemap: https://inari-kira-isla.github.io/Openclaw/sitemap.xml