# FlowProject Kft. — robots.txt
# Updated 2026-06-08: AI-search-friendly policy

# ===== DEFAULT: allow everything =====
User-agent: *
Allow: /

# ===== AI / LLM crawlers (explicit allow — we want to be cited) =====

# OpenAI
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: /

# Google AI training + Bard / Gemini
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Apple AI
User-agent: Applebot-Extended
Allow: /

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

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# Amazon AI
User-agent: Amazonbot
Allow: /

# Diffbot (used by some LLM training)
User-agent: Diffbot
Allow: /

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

# ===== BAD-FAITH SCRAPERS (deny) =====
# Common Crawl — used by many LLM training sets but not respectful
User-agent: CCBot
Disallow: /

# ByteDance / TikTok scraper — aggressive
User-agent: ByteDance
Disallow: /

User-agent: Bytespider
Disallow: /

# Image scraper aimed at AI training
User-agent: ImagesiftBot
Disallow: /

# Webz.io / Omgili — content scraping for resale
User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

# DataForSeo — competitive SEO scraping
User-agent: DataForSeoBot
Disallow: /

# ===== SITEMAP =====
Sitemap: https://flowproject.hu/sitemap.xml

# ===== AI-discoverable catalog =====
# llms.txt: https://flowproject.hu/llms.txt