# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# robots.txt for the MeshCore Analyzer.
#
# This is advisory only: a well-behaved crawler obeys it, a scraper ignores it.
# The enforced defences are elsewhere — the origin only accepts traffic through
# Cloudflare (deploy/web/Caddyfile's (cfonly) guard) and every read API rate
# limits per client (internal/ratelimit). This file just tells the polite bots
# not to bother.
#
# The JSON APIs and the live stream are polled data endpoints, not indexable
# pages, so no crawler has any reason to walk them; a bot looping over them is
# exactly the automated pulling we want to discourage. The site itself is a
# hash-routed single-page app, so its content is not made of separate crawlable
# URLs anyway — indexing the entry document is all a search engine can do.

User-agent: *
Disallow: /api/
Disallow: /stream
Disallow: /embed/

# Bulk content harvesters (AI training and dataset crawlers). These exist to
# copy whole sites, which is the opposite of what this data is served for, so
# they are asked off entirely. Ones that ignore robots.txt are caught by the
# rate limit instead.
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /