# Harmny - robots.txt
# https://harmny.ai

User-agent: *
Content-Signal: search=yes, ai-train=no, ai-input=yes
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /internal/

# /app/ and /tasks/ intentionally crawlable so Googlebot can see the
# X-Robots-Tag: noindex, nofollow header served by Express. Blocking them
# in robots.txt prevents re-crawl, which leaves already-indexed URLs
# stuck in the index. Re-add Disallow once GSC confirms they're dropped.

# ─── AI Search Crawlers (allowed — we want AI search citations) ───
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Timpibot
Allow: /

# ─── Block aggressive/unwanted bots ───
User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgili
Disallow: /

# Content Signals — AI content-usage preferences (https://contentsignals.org/,
# draft-romm-aipref-contentsignals). Declared in the User-agent: * group above:
#   search=yes    — allow indexing for search results & AI search answers
#   ai-train=no   — opt OUT of using our content to train AI models
#   ai-input=yes  — allow use as real-time AI answer input (grounding/RAG)
# Note: the Lighthouse robots.txt validator flags this non-RFC-9309 directive as an
# error (minor SEO-audit cost) — accepted deliberately to assert the no-training stance.

# Sitemap & IndexNow
Sitemap: https://harmny.ai/sitemap-index.xml

# IndexNow key for instant Bing/Yandex/Naver indexing
# Key file: https://harmny.ai/88882660f4a64623920fbc920ba2a00d.txt