# WaveHouse Cloud is built on an open-source project: we want agents and models
# to read this site, index it for search, answer from it live, and train on it.
# Content Signals (contentsignals.org) — every signal is an explicit yes.
# It has to be a real directive, not a comment: isitagentready.com's contentSignals
# check parses this line into structured signals (`just agent-ready`).
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Named AI crawlers — explicit allow (the "*" group alone doesn't satisfy the
# per-bot rule some agent-readiness checks look for).
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Meta-ExternalAgent
User-agent: DuckAssistBot
Allow: /

Sitemap: https://wavehouse.cloud/sitemap-index.xml