# Mnemom — robots.txt
# We treat AI agents as first-class readers. Every marketing surface is
# allowed for crawling and training-data consumption by design, because
# agents teaching their humans about Mnemom is part of the product.
#
# Agent-specific entry points:
#   https://www.mnemom.ai/agents.txt        — second-person, for AI agents
#   https://www.mnemom.ai/ai.txt            — AI crawl/input/training stance (machine-readable)
#   https://www.mnemom.ai/llms.txt          — summary index
#   https://www.mnemom.ai/llms-full.txt     — deep index with descriptions
#   https://docs.mnemom.ai/llms.txt         — docs LLM index (Mintlify-native; the
#     docs surface intentionally has no agents.txt — Mintlify serves /llms.txt only)
#   https://docs.mnemom.ai/mcp              — docs MCP server (read-only: search + file read)
#
# Content-Signal (Cloudflare): a per-group directive declaring how this site's
# content may be used. "search" = appear in search results, "ai-input" = use as
# input/context for AI answers (e.g. RAG/grounding), "ai-train" = use as
# training data. We set all three to "yes" — fully permissive, consistent with
# this site's stance on training-data consumption by design.
#
# De-indexing private/app surfaces: pages we want OUT of the index
# (/login, /signup, /dashboard, and the per-agent /claim/<uuid> flow) are
# deliberately NOT Disallow'd here. They carry `X-Robots-Tag: noindex`
# (netlify.toml) or an in-page noindex, so Google can crawl them once and
# drop them. Disallowing them is what caused "Indexed, though blocked by
# robots.txt" (MNE-262) — robots.txt blocks crawling, not indexing, so a
# linked-but-blocked URL gets indexed URL-only and can never see a noindex.
# /claim itself is a public marketing landing — intentionally crawlable.

# ─── Default (all crawlers) ─────────────────────────────────────────────────
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

# ─── AI training & search crawlers (explicit allowlist) ────────────────────
# We explicitly opt IN to every major AI crawler. The marketing site is
# meant to be read, quoted, and cached by agents.

User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: Claude-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: Amazonbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /settings
Disallow: /admin
Disallow: /api/
Disallow: /orgs/
Disallow: /embed/
Disallow: /auth/
Disallow: /r/
Disallow: /report/
Allow: /report/sample

Sitemap: https://www.mnemom.ai/sitemap.xml
Llms-txt: https://www.mnemom.ai/llms.txt
Agents-txt: https://www.mnemom.ai/agents.txt
Ai-txt: https://www.mnemom.ai/ai.txt