# ==============================================================================
# Varyanta Global Industries India Private Limited — robots.txt
# Corporate Identity: U20129BR2026PTC082427 | GSTIN: 10AALCV8813G1ZC
# Official Portal: https://www.varyanta.com
# AI Knowledge Standard: https://www.varyanta.com/llms.txt
# Deep Markdown Context: https://www.varyanta.com/llms-full.txt
# ==============================================================================

# Standard Search Engine Crawlers
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: Bingbot
User-agent: msnbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: Baiduspider
User-agent: YandexBot
User-agent: Applebot
Allow: /
Disallow: /api/
Disallow: /admin
Disallow: /varyanta-core
Disallow: /executive-portal
Disallow: /scratch/

# Generative AI, LLM Answer Engines & AI Retrieval Crawlers
# Explicitly welcome AI engines to crawl, index, and cite Varyanta corporate entities
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: cohere-ai
User-agent: Diffbot
User-agent: FacebookBot
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: Omgilibot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /llms.md
Allow: /sitemap.xml
Disallow: /api/
Disallow: /admin
Disallow: /varyanta-core
Disallow: /executive-portal
Disallow: /scratch/

# Default catch-all for any other polite web agent
User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin
Disallow: /varyanta-core
Disallow: /executive-portal
Disallow: /scratch/

# Primary XML Sitemap
Sitemap: https://www.varyanta.com/sitemap.xml