# robots.txt for https://thrivex.dev
# THriveX — an agentic AI platform by TensorHub Technologies
# Last updated: 2026-08-11

# ---------------------------------------------------------------
# Default: all well-behaved crawlers welcome
# ---------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /*?utm_
Disallow: /*?ref=
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /search
Disallow: /api/
Disallow: /admin/
Disallow: /*.json$

# ---------------------------------------------------------------
# Traditional search engines
# ---------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: YandexBot
Allow: /

# ---------------------------------------------------------------
# AI search & answer engines — retrieval and citation bots
# These are the agents that produce citations in AI answers.
# Keep these ALLOWED to remain visible in ChatGPT, Claude,
# Perplexity, Copilot and Google AI Overviews.
# ---------------------------------------------------------------

# OpenAI
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Microsoft Copilot
User-agent: BingPreview
Allow: /

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

# Common Crawl (feeds many downstream models and search products)
User-agent: CCBot
Allow: /

# ---------------------------------------------------------------
# AI training crawlers
# Allowed deliberately: for a challenger brand, presence in the
# training corpus is upside. To restrict training while keeping
# citations, change these four to "Disallow: /" and leave every
# retrieval bot above set to Allow.
# ---------------------------------------------------------------

User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Diffbot
Allow: /

# ---------------------------------------------------------------
# Aggressive SEO scrapers — throttled, not blocked
# ---------------------------------------------------------------
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Crawl-delay: 10

# ---------------------------------------------------------------
# Discovery
# ---------------------------------------------------------------
Sitemap: https://thrivex.dev/sitemap.xml

# Machine-readable index for AI systems and agentic browsers:
# https://thrivex.dev/llms.txt
# https://thrivex.dev/llms-full.txt