diff --git a/public/robots.txt b/public/robots.txt index 836c209..206832c 100644 --- a/public/robots.txt +++ b/public/robots.txt @@ -1,39 +1,226 @@ # DEV LEDGER — crawler policy -# Public product and documentation pages are intentionally discoverable. -# Authenticated application surfaces, API routes, and telemetry relays are not. -# Updated: 2026-09-28 +# Public product, documentation, security, legal, and journal pages are discoverable. +# Authenticated application surfaces, APIs, and telemetry relays are not. +# Search and answer-engine discovery is allowed. +# Dedicated model-training/data-corpus crawlers are blocked. +# Updated: 2026-10-04 + + +# ================================================== +# DEFAULT POLICY +# ================================================== User-agent: * Allow: / + +Disallow: /api/ +Disallow: /rly/ +Disallow: /overview +Disallow: /projects +Disallow: /activity +Disallow: /code +Disallow: /shipping + + +# ================================================== +# GOOGLE SEARCH +# ================================================== + +User-agent: Googlebot +User-agent: Googlebot-Image +User-agent: Googlebot-Video +User-agent: Googlebot-News +Allow: / + +Disallow: /api/ +Disallow: /rly/ +Disallow: /overview +Disallow: /projects +Disallow: /activity +Disallow: /code +Disallow: /shipping + + +# ================================================== +# MICROSOFT BING +# ================================================== + +User-agent: Bingbot +Allow: / + +Disallow: /api/ +Disallow: /rly/ +Disallow: /overview +Disallow: /projects +Disallow: /activity +Disallow: /code +Disallow: /shipping + + +# ================================================== +# DUCKDUCKGO +# ================================================== + +User-agent: DuckDuckBot +Allow: / + +Disallow: /api/ +Disallow: /rly/ +Disallow: /overview +Disallow: /projects +Disallow: /activity +Disallow: /code +Disallow: /shipping + + +# ================================================== +# YANDEX +# ================================================== + +User-agent: YandexBot +Allow: / + Disallow: /api/ Disallow: /rly/ Disallow: /overview +Disallow: /projects Disallow: /activity Disallow: /code +Disallow: /shipping + + +# ================================================== +# BAIDU +# ================================================== + +User-agent: Baiduspider +Allow: / + +Disallow: /api/ +Disallow: /rly/ +Disallow: /overview +Disallow: /projects +Disallow: /activity +Disallow: /code +Disallow: /shipping + + +# ================================================== +# OPENAI — SEARCH / RETRIEVAL +# ================================================== -# AI search, answer, retrieval, and model crawlers. -# Discoverability-first policy: public pages are allowed; private/app surfaces remain blocked. User-agent: OAI-SearchBot -User-agent: GPTBot User-agent: ChatGPT-User -User-agent: ClaudeBot +Allow: / + +Disallow: /api/ +Disallow: /rly/ +Disallow: /overview +Disallow: /projects +Disallow: /activity +Disallow: /code +Disallow: /shipping + + +# ================================================== +# ANTHROPIC — SEARCH / USER RETRIEVAL +# ================================================== + User-agent: Claude-SearchBot User-agent: Claude-User +Allow: / + +Disallow: /api/ +Disallow: /rly/ +Disallow: /overview +Disallow: /projects +Disallow: /activity +Disallow: /code +Disallow: /shipping + + +# ================================================== +# PERPLEXITY — SEARCH / RETRIEVAL +# ================================================== + User-agent: PerplexityBot User-agent: Perplexity-User -User-agent: Google-Extended +Allow: / + +Disallow: /api/ +Disallow: /rly/ +Disallow: /overview +Disallow: /projects +Disallow: /activity +Disallow: /code +Disallow: /shipping + + +# ================================================== +# APPLE SEARCH +# ================================================== + User-agent: Applebot -User-agent: Applebot-Extended -User-agent: meta-webindexer -User-agent: meta-externalagent +Allow: / + +Disallow: /api/ +Disallow: /rly/ +Disallow: /overview +Disallow: /projects +Disallow: /activity +Disallow: /code +Disallow: /shipping + + +# ================================================== +# META — USER RETRIEVAL +# Allow user-requested fetching while keeping Meta's +# dedicated training/indexing agents blocked below. +# ================================================== + User-agent: meta-externalfetcher -User-agent: CCBot -User-agent: Bytespider Allow: / + Disallow: /api/ Disallow: /rly/ Disallow: /overview +Disallow: /projects Disallow: /activity Disallow: /code +Disallow: /shipping + + +# ================================================== +# MODEL TRAINING / DATA-CORPUS CRAWLERS +# ================================================== + +User-agent: GPTBot +Disallow: / + +User-agent: ClaudeBot +Disallow: / + +User-agent: Google-Extended +Disallow: / + +User-agent: Applebot-Extended +Disallow: / + +User-agent: CCBot +Disallow: / + +User-agent: Bytespider +Disallow: / + +User-agent: meta-externalagent +Disallow: / + +User-agent: meta-webindexer +Disallow: / + + +# ================================================== +# SITEMAP +# ================================================== Sitemap: https://devledger.site/sitemap.xml