# robots.txt for sparai.org
#
# As a condition of accessing this website, you agree to abide by the following
# content signals:
#
# (a)  If a content-signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a content-signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a content signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via content signal with respect to the corresponding use.
#
# The content signals and their meanings are:
#
# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
#
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# Default: Allow search and AI-input (RAG/grounding), but no training
User-Agent: *
Content-signal: search=yes,ai-input=yes,ai-train=no
Allow: /

# ClaudeBot (Anthropic): Allow everything including training
User-agent: ClaudeBot
Content-signal: search=yes,ai-input=yes,ai-train=yes
Allow: /

# Block crawlers known to ignore robots.txt or content signals
User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

Sitemap: https://sparai.org/sitemap-index.xml