# local-ci.dev
# Crawl rules for search engines and AI agents.
# Reference: RFC 9309 (https://www.rfc-editor.org/rfc/rfc9309)

Sitemap: https://local-ci.dev/sitemap.xml

# Content Signals declare our preferences for how content may be used.
# Reference: https://contentsignals.org/
#   search    — allow indexing for search engines
#   ai-input  — allow grounding / retrieval for AI answers
#   ai-train  — do not use for training generative models
Content-Signal: search=yes, ai-input=yes, ai-train=no

# Default: everything is crawlable.
User-agent: *
Allow: /

# --- Search ---

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# --- Google AI (Gemini / Vertex) — opt-in separately from Googlebot ---

User-agent: Google-Extended
Allow: /

# --- OpenAI ---

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: /

# --- Perplexity ---

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# --- Apple ---

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# --- Common Crawl ---

User-agent: CCBot
Allow: /

# --- Meta ---

User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# --- ByteDance ---

User-agent: Bytespider
Allow: /

# --- DuckDuckGo assistant ---

User-agent: DuckAssistBot
Allow: /
