# DCMI allows all crawlers, including AI training, search, and retrieval bots.
# DCMI's mission is open metadata standards; broad machine readability
# supports that mission. Explicit per-agent entries follow RFC 9309 best
# practice and satisfy validators that require more than a wildcard rule.
#
# Content-Signal declares DCMI's usage preferences per the AIPREF draft
# (draft-romm-aipref-contentsignals): all three signals are affirmative.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- OpenAI ---
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Anthropic ---
User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Claude-Web
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Claude-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Google ---
User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: GoogleOther
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Apple ---
User-agent: Applebot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Microsoft / Bing ---
User-agent: bingbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Meta ---
User-agent: Meta-ExternalAgent
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Meta-ExternalFetcher
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: FacebookBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Amazon ---
User-agent: Amazonbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Perplexity ---
User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Cohere ---
User-agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: cohere-training-data-crawler
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Mistral ---
User-agent: MistralAI-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- ByteDance / TikTok ---
User-agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Common Crawl (training data for many LLMs) ---
User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- You.com ---
User-agent: YouBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- DuckDuckGo ---
User-agent: DuckAssistBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Allen Institute for AI ---
User-agent: AI2Bot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: AI2Bot-Dolma
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Huawei ---
User-agent: PanguBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Timpi ---
User-agent: Timpibot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Diffbot ---
User-agent: Diffbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- ImagesiftBot (The Hive) ---
User-agent: ImagesiftBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Omgili / Webz.io ---
User-agent: Omgili
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: omgilibot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Webzio-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- Misc AI training / agentic crawlers ---
User-agent: FriendlyCrawler
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: ISSCyberRiskCrawler
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Kangaroo Bot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: iaskspider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Iaskspider/2.0
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: SemrushBot-OCOB
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Velen Crawler
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Scrapy
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Sidetrade indexer bot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

Sitemap: https://www.dublincore.org/sitemap.xml