# =====================================================================
# robots.txt for Innomerc Tech Pvt. Ltd
# https://www.innomerctech.com.np/
# Last updated: 2026 07 13
# =====================================================================

# Default policy: public website content is crawlable.
# Private folders and repository/tooling files are not crawlable.
User-agent: *
Allow: /
Allow: /css/
Allow: /js/
Allow: /images/
Allow: /services/
Allow: /insights/
Allow: /llms.txt
Allow: /site-map
Allow: /sitemap.xml
Disallow: /.claude/
Disallow: /.git/

# CSS, JavaScript and images are intentionally crawlable.
# Search engines and AI answer engines need these files to render and understand the website properly.


# =====================================================================
# Block aggressive SEO crawlers and non-search scrapers
# These are not needed for public search indexing or AI answer visibility.
# =====================================================================

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /


# =====================================================================
# Major search engines and discovery crawlers
# =====================================================================

User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-Video
User-agent: Google-InspectionTool
User-agent: Bingbot
User-agent: msnbot
User-agent: BingPreview
User-agent: DuckDuckBot
User-agent: Slurp
User-agent: YandexBot
User-agent: Baiduspider
User-agent: Sogou web spider
User-agent: Sogou inst spider
User-agent: SeznamBot
User-agent: Yeti
User-agent: Bravebot
User-agent: Qwantify
User-agent: MojeekBot
User-agent: PetalBot
Allow: /
Allow: /css/
Allow: /js/
Allow: /images/
Allow: /services/
Allow: /insights/
Allow: /llms.txt
Allow: /site-map
Allow: /sitemap.xml
Disallow: /.claude/
Disallow: /.git/


# =====================================================================
# AI answer engines, LLM crawlers and user-triggered fetchers
# This supports ChatGPT, Google AI/Gemini, Claude, Perplexity, You.com,
# Grok/xAI, DeepSeek-style crawlers and other LLM assistants that respect robots.txt.
# =====================================================================

User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: Google-CloudVertexBot
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: YouBot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: cohere-ai
User-agent: FacebookBot
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: Bytespider
User-agent: Amazonbot
User-agent: Diffbot
User-agent: xAI-Bot
User-agent: GrokBot
User-agent: xAI-SearchBot
User-agent: DeepSeekBot
User-agent: DeepSeek
Allow: /
Allow: /css/
Allow: /js/
Allow: /images/
Allow: /services/
Allow: /insights/
Allow: /llms.txt
Allow: /site-map
Allow: /sitemap.xml
Disallow: /.claude/
Disallow: /.git/


# =====================================================================
# AI reference file
# =====================================================================

# AI-Content-Guide: https://www.innomerctech.com.np/llms.txt


# =====================================================================
# Sitemap
# =====================================================================

Sitemap: https://www.innomerctech.com.np/sitemap.xml