Search

# ============================================================
# Akua — robots.txt
# Allows search + AI citation/training crawlers explicitly.
# Per Google's official docs (2024+): `Google-Extended` controls
# AI Overviews / Gemini training only — it does NOT impact a
# site's inclusion or ranking in Google Search.
# ============================================================

# ---------- Standard search ----------
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# ---------- AI search & citation crawlers ----------
# These produce direct citation surface in ChatGPT, Perplexity,
# Claude, Copilot, and Google AI Overviews / Gemini.
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# ---------- AI training crawlers ----------
# Allowed by default; revisit quarterly if content becomes a
# competitive moat that should not feed model training.
User-agent: GPTBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# ---------- Opaque / aggressive crawlers ----------
User-agent: Bytespider
Disallow: /

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

# ---------- Universal ----------
# Non-public routes that should never be crawled. The blog,
# marketing pages, and category pages are explicitly open.
User-agent: *
Allow: /
Disallow: /api/
Disallow: /auth/
Disallow: /login
Disallow: /logout
Disallow: /deploy/
Disallow: /email-previews
Disallow: /survey
Disallow: /settings
Disallow: /products
Disallow: /apps
Disallow: /clusters
Disallow: /installations

Sitemap: https://akua.dev/sitemap.xml