# robots.txt for nextomoro.com
# AI Research Lab Intelligence
# Policy: open to all well-behaved crawlers, including AI/LLM crawlers.
# Last reviewed: 2026-04-26

# ---------------------------------------------------------------------------
# Default rule: allow all crawlers, block only Ghost internals.
# ---------------------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /ghost/
Disallow: /p/
Disallow: /email/
Disallow: /r/
Disallow: /webmentions/receive/
Disallow: /members/api/
Disallow: /.ghost/
Disallow: /*?ref=
Disallow: /*?source=
Disallow: /*?utm_

# Make sure renderable assets stay crawlable so Google can render the page.
Allow: /assets/
Allow: /content/images/
Allow: /public/
Allow: /*.css$
Allow: /*.js$
Allow: /*.svg$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.webp$
Allow: /*.avif$
Allow: /*.gif$
Allow: /*.ico$
Allow: /*.woff$
Allow: /*.woff2$

# ---------------------------------------------------------------------------
# Search engines — explicit allow blocks (no surprises, no crawl-delay).
# ---------------------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Pinterestbot
Allow: /

# ---------------------------------------------------------------------------
# AI / LLM crawlers — fully opted in.
# Training crawlers, retrieval crawlers, and live answer-engine crawlers.
# ---------------------------------------------------------------------------

# 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: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Google AI (separate from Googlebot — controls Gemini training/grounding)
User-agent: Google-Extended
Allow: /

# Apple Intelligence (separate from Applebot)
User-agent: Applebot-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# ByteDance / Doubao
User-agent: Bytespider
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

# DuckAssistBot (DuckDuckGo AI)
User-agent: DuckAssistBot
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Diffbot (knowledge-graph crawlers)
User-agent: Diffbot
Allow: /

# Common Crawl (training data for many open models)
User-agent: CCBot
Allow: /

# Image / multimodal crawlers
User-agent: ImagesiftBot
Allow: /

User-agent: img2dataset
Allow: /

# Other named LLM crawlers
User-agent: Timpibot
Allow: /

User-agent: omgili
Allow: /

User-agent: omgilibot
Allow: /

User-agent: Kagibot
Allow: /

User-agent: PetalBot
Allow: /

# Internet Archive (preserves the site for historical reference)
User-agent: ia_archiver
Allow: /

User-agent: archive.org_bot
Allow: /

# ---------------------------------------------------------------------------
# Sitemaps
# ---------------------------------------------------------------------------
Sitemap: https://nextomoro.com/sitemap.xml
Sitemap: https://nextomoro.com/sitemap-pages.xml
Sitemap: https://nextomoro.com/sitemap-posts.xml
Sitemap: https://nextomoro.com/sitemap-authors.xml
Sitemap: https://nextomoro.com/sitemap-tags.xml

# Host preference (used by Yandex; harmless for others)
Host: https://nextomoro.com