# heardofyou.io robots.txt
# We want AI assistants and search engines to read and cite our public pages.
# Search crawlers and training crawlers are both allowed, on purpose.
# Only private result pages and the API are blocked.
# Why: https://heardofyou.io/guides/what-works-and-what-doesnt

User-agent: *
Allow: /
Disallow: /r/
Disallow: /report
Disallow: /report/
Disallow: /api/

# Named explicitly so the decision is visible. Same rules as above.

# Search engines (Brave Search follows the Googlebot rules; Bravebot named in case it is used)
User-agent: Googlebot
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: YandexBot
User-agent: Bravebot
# OpenAI: search, user-triggered fetch, training
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
# Anthropic: training, search, user-triggered fetch
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: anthropic-ai
# Perplexity: index and user-triggered fetch
User-agent: PerplexityBot
User-agent: Perplexity-User
# Google AI training (Search and AI Overviews use Googlebot above)
User-agent: Google-Extended
# Common Crawl, Apple, ByteDance
User-agent: CCBot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Bytespider
# Meta, Amazon (Alexa, Rufus), DuckDuckGo AI answers
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: Amazonbot
User-agent: DuckAssistBot
Allow: /
Disallow: /r/
Disallow: /report
Disallow: /report/
Disallow: /api/

Sitemap: https://heardofyou.io/sitemap.xml