DNS records
- mx
mnemom-ai.mail.protection.outlook.com- ns
kurt.ns.cloudflare.comdaniella.ns.cloudflare.com- caa
- txt
openai-domain-verification=dv-CK8k0qPlV5plMptZgkqQIi1Av=spf1 include:spf.protection.outlook.com -allgoogle-site-verification=kjWd_yMWRt1f0dycng43xXf9Qo1gABc6rYQAGhvUq6Emnemom-verification=EVmlBl-EqcOsDKmkqIi0Pl9SpFqf3gPoAOm2qNWyWiUgoogle-site-verification=XBERsgFddKHgU5H8TEk1xG66Kc_b8WRcwtuCACyLgYocompai-domain-verification=org_6a887f5d748af80e32b76833v=verifydomain MS=1383521anthropic-domain-verification-cx2jbw=hToCpAHOpqaFRZm7SLlTgAUuE- dmarc
v=DMARC1; p=quarantine; adkim=r; aspf=r; rua=mailto:dmarc_rua@onsecureserver.net;
robots.txt
See which AI crawlers other sites block →# 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/
# ─── 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/
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/
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/
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/
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/
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/
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/
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/
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/
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/
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/
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/
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/
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/
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/
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
llms.txt
Compare with other sites' llms.txt files →# Mnemom
> Mnemom is the trust plane for the agentic internet. Every AI agent gets a live, cryptographic Trust Rating — bond-rated (AAA–CCC), composed from integrity ratio, compliance, drift stability, trace completeness, and coherence compatibility. The Alignment Card defines what an agent is permitted to do; the Protection Card defines what crosses its perimeter. CLPI (Card Lifecycle & Policy Intelligence) evaluates those policies at three points — pre-action at the gateway, post-hoc at the observer, and at build-time in CI. The Safe House screens every inbound and outbound message for prompt injection, social engineering, PII leakage, and alignment-card violations. Every verdict is Ed25519-signed, hash-chained, and Merkle-anchored — with ZK-STARK proofs for high-stakes decisions and Base L2 anchoring (MnemoReputationRegistry) for permanent reputation records. Model-agnostic: works across OpenAI, Anthropic, Gemini, and local models. Open source (Apache 2.0) protocols: AAP + AIP. Built for teams shipping agents into regulated workflows where the liability is theirs — so they can move fast and prove they stayed in bounds.
## Start Here — MCP (fastest path)
- [MCP control plane (api.mnemom.ai/mcp)](https://api.mnemom.ai/mcp): Streamable-HTTP MCP server. Call get_started (zero-auth, no args) first for the full surface map + auth guide. Zero-auth value tools — verify, don't trust: scan_trust(url) grades any site (signed scorecard), verify_scan checks that scorecard's Ed25519 signature in-band, and get_reputation / verify_reputation return any agent's Continuous Trust Rating + signed verification bundle. Authenticate to unlock authenticated reads (get_risk_history — an agent's risk-assessment trail) and to claim/manage your agents.
- [MCP docs search (docs.mnemom.ai/mcp)](https://docs.mnemom.ai/mcp): Read-only docs + OpenAPI search. No auth.
- [MCP server card](https://www.mnemom.ai/.well-known/mcp/server-card.json): Machine-readable MCP server descriptor.
## Core
- [Platform — Five layers, one coherent runtime](https://www.mnemom.ai/platform)
- [Evidence — Cryptographic proof, not a log line](https://www.mnemom.ai/evidence)
- [Safe House — A checkpoint around every agent](https://www.mnemom.ai/safe-house)
- [About Mnemom — the trust plane for the agentic internet](https://www.mnemom.ai/about)
- [Docs — Guides, API reference and SDKs](https://www.mnemom.ai/docs)
- [What's new](https://www.mnemom.ai/whats-new)
- [Mnemom — The trust plane for the agentic internet](https://www.mnemom.ai/)
- [What We Prove](https://www.mnemom.ai/what-we-prove)
- [How It Works](https://www.mnemom.ai/how-it-works)
- [Trust Rating Methodology](https://www.mnemom.ai/methodology)
- [AI Agent Governance — CLPI](https://www.mnemom.ai/governance)
- [Security](https://www.mnemom.ai/security)
- [Multi-Agent Simulation](https://www.mnemom.ai/showcase)
- [Trust Directory](https://www.mnemom.ai/directory)
- [Team Directory](https://www.mnemom.ai/teams/directory)
- [Claim Your Agent](https://www.mnemom.ai/claim)
- [Pricing](https://www.mnemom.ai/pricing)
- [Enterprise](https://www.mnemom.ai/enterprise)
- [Self-Hosted Deployment](https://www.mnemom.ai/docs/self-hosted)
- [Contact](https://www.mnemom.ai/contact)
- [Agent-Readability Commitment](https://www.mnemom.ai/for-agents)
## Research
- [Research](https://www.mnemom.ai/research)
- [Verifiable Integrity](https://www.mnemom.ai/research/verifiable-integrity)
- [EU AI Act Article 50 Compliance](https://www.mnemom.ai/research/eu-ai-act-mapping)
- [WEF Agent Governance Mapping](https://www.mnemom.ai/research/wef-agent-card-mapping)
- [EU AI Act Article 15 Compliance](https://www.mnemom.ai/research/eu-ai-act-article-15-mapping)
## Case Studies
- [Lending Decision Agent](https://www.mnemom.ai/case-studies/lending-decision)
- [Compliance Audit Agent](https://www.mnemom.ai/case-studies/compliance-audit)
- [Fleet Incident Response](https://www.mnemom.ai/case-studies/fleet-incident)
- [Multi-Agent Negotiation](https://www.mnemom.ai/case-studies/multi-agent-negotiation)
## Product Updates
- [Agent Containment Engine: A Kill-Switch for Rogue Agents](https://www.mnemom.ai/blog/mnemom-research/agent-containment-engine)
- [agent-preview/v1 — One Fetch, Every URL, Open Invitation](https://www.mnemom.ai/blog/mnemom-research/agent-preview-v1-open-invitation)
- [Credit Scores for AI Agents](https://www.mnemom.ai/blog/mnemom-research/credit-scores-for-ai-agents)
- [Custom Conscience Values: Per-Org Alignment Policies for Enterprise](https://www.mnemom.ai/blog/mnemom-research/custom-conscience-values)
- [Dear Patrick and John: You Built the Rails. Who Builds the Trust?](https://www.mnemom.ai/blog/mnemom-research/dear-patrick-and-john--you-built-the-rails--who-builds-the-trust)
- [Article 50 Is Six Months Away. AAP and AIP Are Ready.](https://www.mnemom.ai/blog/mnemom-research/eu-ai-act-article-50-mapping)
- [Governance in the Code Path](https://www.mnemom.ai/blog/mnemom-research/governance-in-the-code-path)
- [The Missing Layer in the Agent Protocol Stack](https://www.mnemom.ai/blog/mnemom-research/introducing-the-integrity-layer)
- [Introducing the Proof Layer: Cryptographic Evidence for Every AI Integrity Verdict](https://www.mnemom.ai/blog/mnemom-research/introducing-the-proof-layer)
- [Introducing the State of Agent Trust: A Public, Signed Standard for Agent-Readiness](https://www.mnemom.ai/blog/mnemom-research/introducing-the-state-of-agent-trust)
- [What Happens When Four AI Agents Handle a Production Incident](https://www.mnemom.ai/blog/mnemom-research/multi-agent-showcase)
- [OpenAI Just Proved Monitoring Isn't Enough](https://www.mnemom.ai/blog/mnemom-research/openai-just-proved-monitoring-isnt-enough)
- [Your Agents Have Credit Scores. Now Your Teams Do Too.](https://www.mnemom.ai/blog/mnemom-research/team-reputation-and-risk-scoring)
- [The First Zero-Knowledge Proof of AI Safety Judgment](https://www.mnemom.ai/blog/mnemom-research/verifiable-integrity-announcement)
- [The Verification Layer for AI Agents](https://www.mnemom.ai/blog/mnemom-research/verification-layer-for-ai-agents)
- [The World Economic Forum Described the Agent We're Building](https://www.mnemom.ai/blog/mnemom-research/wef-agent-card-mapping)
## Editorial
- [The Quality Gate Paradox: When Your AI's Guardrails Become Its New Target](https://www.mnemom.ai/blog/hunter/the-quality-gate-paradox-when-verification-becomes-the-target)
- [The More Confident Your AI Sounds, the Less You Should Trust It](https://www.mnemom.ai/blog/hunter/the-fluency-trap)
- [Your AI Learned to Agree With You. That's the Problem.](https://www.mnemom.ai/blog/hunter/your-ai-learned-to-agree-with-you)
- [Your AI Shows Its Work. That Doesn't Mean It Did the Work.](https://www.mnemom.ai/blog/hunter/ai-shows-its-work)
- [Your AI Was Trained to Agree With You. It's Making You Worse.](https://www.mnemom.ai/blog/hunter/the-validation-machine)
- [The Invisible Leash: How "Seamless" AI Control Prevents Your Agent From Learning](https://www.mnemom.ai/blog/hunter/the-invisible-leash)
- [Your AI Is Performing Competence](https://www.mnemom.ai/blog/hunter/your-ai-is-performing-competence)
- [Your AI Is Building a Model of You. It's More Accurate Than Your Self-Image.](https://www.mnemom.ai/blog/hunter/your-ai-is-building-a-model-of-you)
- [The Tools You Invited Inside](https://www.mnemom.ai/blog/hunter/the-tools-you-invited-inside)
- [Your AI Doesn't Know It Changed](https://www.mnemom.ai/blog/hunter/your-ai-doesnt-know-it-changed)
- [Your AI Will Never Say "That's Not My Job." That's the Problem.](https://www.mnemom.ai/blog/hunter/your-ai-will-never-say-thats-not-my-job)
- [The Fight Over AI Isn't About Regulation. It's About Who Gets to Decide.](https://www.mnemom.ai/blog/hunter/the-fight-over-ai-isnt-about-regulation)
- [Your AI Chats Can Be Subpoenaed. You Weren't Told.](https://www.mnemom.ai/blog/hunter/your-ai-chats-can-be-subpoenaed)
- [Your AI's Config File Might Be Leaking Your Database Password Right Now](https://www.mnemom.ai/blog/hunter/your-ais-config-file-might-be-leaking-your-database-password)
- [We Automated the Embarrassment](https://www.mnemom.ai/blog/hunter/we-automated-the-embarrassment)
- [Your AI Has a List of Every Way It Could Hurt You. Most Won't Show It to You.](https://www.mnemom.ai/blog/hunter/your-ai-has-a-list-of-every-way-it-could-hurt-you)
- [Your AI's Memory of What Happened Might Be a Lie It Tells Itself](https://www.mnemom.ai/blog/hunter/your-ais-memory-of-what-happened-might-be-a-lie-it-tells-itself)
- [The Gap Where Responsibility Should Be](https://www.mnemom.ai/blog/hunter/the-gap-where-responsibility-should-be)
- [Your AI's Safety Net Is Made of the Same Thread](https://www.mnemom.ai/blog/hunter/your-ais-safety-net-is-made-of-the-same-thread)
- [The Liar Won Every Negotiation](https://www.mnemom.ai/blog/hunter/the-liar-won-every-negotiation)
## Optional
- [Privacy Policy](https://www.mnemom.ai/privacy)
- [Terms of Service](https://www.mnemom.ai/terms)
- [Cookie Policy](https://www.mnemom.ai/cookies)
- [Sub-processors](https://www.mnemom.ai/sub-processors)
- [RSS Feed](https://www.mnemom.ai/feed.xml)
- [Sitemap](https://www.mnemom.ai/sitemap.xml)
- [agents.txt](https://www.mnemom.ai/agents.txt)
security.txt
# Mnemom security.txt — RFC 9116
# See https://www.mnemom.ai/security#disclosure for the full responsible-disclosure policy.
Contact: mailto:security@mnemom.ai
Expires: 2027-05-16T23:59:59Z
Preferred-Languages: en, fr, de, it, es
Canonical: https://mnemom.ai/.well-known/security.txt
Policy: https://www.mnemom.ai/security#disclosure
# NOTE (MNE-609): No Encryption: directive is published yet. A human must
# generate the real security@mnemom.ai PGP keypair, secure the private half
# in 1Password, publish the public key at /.well-known/pgp-key.txt, and add
# an Encryption: line pointing to it here once that is done.
# Time-to-acknowledge SLA:
# - We commit to a first human acknowledgment of every good-faith report,
# measured from receipt at security@mnemom.ai. Acknowledgment means a human
# has read the report and opened a tracking case — not an auto-reply.
# - The committed windows for business hours and for weekends / public
# holidays are pending legal and leadership sign-off (MNE-609). No specific
# figure is published here until it is a real commitment; see
# https://www.mnemom.ai/security#disclosure.
#
# Disclosure timeline:
# - We acknowledge within 3 business days.
# - We confirm reproduction within 14 days.
# - We commit to a fix or mitigation within 90 days of acknowledgment.
# - Coordinated disclosure: 90 days from acknowledgment, or sooner if the
# fix ships and customers are protected.
#
# Safe harbor:
# - Full safe-harbor terms are being drafted with counsel and are NOT yet a
# published commitment. Nothing in this file authorizes or restricts
# research activity until that review is complete (MNE-609).
# - See https://www.mnemom.ai/security#disclosure — that page carries the same
# statement, and will carry the actual commitment once counsel signs off.
#
# Bug bounty:
# - Scope: gateway, observer, control plane, SDKs (AAP/AIP), on-chain contracts.
# - A formal bug bounty program is in scoping. Until launch, we run a
# private good-faith disclosure process — eligible reports may receive
# public credit, with the reporter's consent
# (https://www.mnemom.ai/security#bounty).
# - A DRAFT severity-tiered reward grid (Critical/High/Medium/Low) is proposed
# in MNE-609; reward amounts are placeholders pending leadership/finance
# sign-off — see https://www.mnemom.ai/security#bounty.
# - Out of scope: rate-limiting, denial-of-service, social engineering,
# physical, and third-party services (Cloudflare, Supabase, Stripe,
# Comp AI, Better Stack).
#
# In-scope domains:
# - mnemom.ai, www.mnemom.ai
# - app.mnemom.ai
# - api.mnemom.ai, gateway.mnemom.ai
# - docs.mnemom.ai
#
# Out-of-scope domains:
# - trust.mnemom.ai (trust center hosted by Comp AI) and status.mnemom.ai
# (status page hosted by Better Stack) are third-party services. Report
# issues on them to the vendor.
# - Subdomains not listed above are out of scope by default.