# robots.txt — ithouse.tech
# Intelligent House of Digital Innovation
# Last updated: 2026-06-12
# https://ithouse.tech

# ============================================================
# DEFAULT: ALL CRAWLERS WELCOME
# ============================================================
User-agent: *
Allow: /
Disallow: /cdn-cgi/
Disallow: /api/
Disallow: /.well-known/
Crawl-delay: 1

# ============================================================
# GOOGLE
# ============================================================
User-agent: Googlebot
Allow: /
Allow: /assets/
Allow: /css/
Allow: /js/

User-agent: Googlebot-Image
Allow: /assets/images/
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: Google-InspectionTool
Allow: /

User-agent: Google-Extended
Allow: /

# ============================================================
# BING / MICROSOFT
# ============================================================
User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: adidxbot
Allow: /

User-agent: msnbot
Allow: /

# ============================================================
# AI CRAWLERS — EXPLICITLY ALLOWED
# ithouse.tech welcomes all AI indexing for GEO citations
# ============================================================

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Meta AI (Llama, Meta AI assistant)
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: facebookexternalhit
Allow: /

# Apple (Siri, Spotlight)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (trains most open-source AI models)
User-agent: CCBot
Allow: /

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

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

# Amazon / Alexa
User-agent: Amazonbot
Allow: /

# Bytedance / TikTok AI
User-agent: Bytespider
Allow: /

# Diffbot (knowledge graphs)
User-agent: Diffbot
Allow: /

# Brave Search
User-agent: Brave-AI
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# ============================================================
# SEO TOOLS — ALLOWED WITH RATE LIMITING
# ============================================================
User-agent: Semrushbot
Allow: /
Crawl-delay: 5

User-agent: SemrushBot-SA
Allow: /
Crawl-delay: 5

User-agent: AhrefsBot
Allow: /
Crawl-delay: 5

User-agent: AhrefsSiteAudit
Allow: /
Crawl-delay: 5

User-agent: DataForSeoBot
Allow: /
Crawl-delay: 5

User-agent: MajesticSEO
Allow: /
Crawl-delay: 5

User-agent: Screaming-Frog-SEO-Spider
Allow: /
Crawl-delay: 5

# ============================================================
# BLOCK AGGRESSIVE SCRAPERS
# ============================================================
User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Yandex
Disallow: /

# ============================================================
# SITEMAPS
# ============================================================
Sitemap: https://ithouse.tech/sitemap.xml

# ============================================================
# HOST
# ============================================================
Host: ithouse.tech