# robots.txt — hellouchit.com
# Last updated 2026-05-30.
# Policy: ALLOW all crawlers, including AI ingestion crawlers.
# The content here is meant to be found, cited, and quoted.

User-agent: *
Allow: /

# ─────────────────────────────────────────────────────────────
# AI ingestion + training crawlers — explicitly allowed.
# Listing them by name signals intent; many default to "deny"
# when the operator hasn't explicitly decided.
# ─────────────────────────────────────────────────────────────

# OpenAI (ChatGPT browsing + crawling + search)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google Gemini & Vertex AI (separate from classic Google search indexing)
User-agent: Google-Extended
Allow: /

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

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

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

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

# Common Crawl (underlying corpus for many open models)
User-agent: CCBot
Allow: /

# Diffbot (knowledge-graph extraction)
User-agent: Diffbot
Allow: /

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

# Bytespider (ByteDance / TikTok / Doubao AI)
User-agent: Bytespider
Allow: /

# DuckDuckGo Assist
User-agent: DuckAssistBot
Allow: /

# Brave Search
User-agent: BraveBot
Allow: /

# ─────────────────────────────────────────────────────────────
# Sitemaps + AI manifest pointer
# ─────────────────────────────────────────────────────────────
Sitemap: https://hellouchit.com/sitemap.xml

# Pointer to the AI-readable manifest (llmstxt.org convention)
# https://hellouchit.com/llms.txt