# Mnemom Docs

## Docs

- [Delete agent](https://docs.mnemom.ai/api-reference/endpoint/delete-agents-agent-id.md): GDPR Article 17 right-to-erasure — permanently deletes an agent and all associated data
- [Reset conscience values to defaults](https://docs.mnemom.ai/api-reference/endpoint/delete-agents-agent-id-conscience-values.md)
- [Remove AIP webhook](https://docs.mnemom.ai/api-reference/endpoint/delete-aip-webhooks-registration-id.md)
- [Revoke an API key](https://docs.mnemom.ai/api-reference/endpoint/delete-api-keys-key-id.md)
- [Delete authenticated user account and unlink agents](https://docs.mnemom.ai/api-reference/endpoint/delete-auth-delete-account.md)
- [Remove an enrolled passkey](https://docs.mnemom.ai/api-reference/endpoint/delete-auth-passkeys-credential-id.md): Requires aal2. Deleting a passkey does not affect other passkeys or the password/MFA fallback; those remain usable.
- [Delete organization (owner only)](https://docs.mnemom.ai/api-reference/endpoint/delete-orgs-org-id.md)
- [Delete organization alignment template](https://docs.mnemom.ai/api-reference/endpoint/delete-orgs-org-id-alignment-template.md): Clears the org alignment template (stored as `null`, `enabled: false`) and flags every member agent for recompose so their canonical cards fall back to platform defaults + agent card. Requires org `owner`/`admin` and `Idempotency-Key`. See ADR-008.
- [Revoke organization API key](https://docs.mnemom.ai/api-reference/endpoint/delete-orgs-org-id-api-keys-key-id.md)
- [Delete org conscience value](https://docs.mnemom.ai/api-reference/endpoint/delete-orgs-org-id-conscience-values-value-id.md): Permanently delete a conscience value. Requires owner or admin role.
- [Revoke a pending invitation](https://docs.mnemom.ai/api-reference/endpoint/delete-orgs-org-id-invitations-invitation-id.md)
- [Remove member or self-leave](https://docs.mnemom.ai/api-reference/endpoint/delete-orgs-org-id-members-user-id.md)
- [Delete organization protection template](https://docs.mnemom.ai/api-reference/endpoint/delete-orgs-org-id-protection-template.md): Clears the org protection template and flags every member agent for recompose. Requires org `owner`/`admin` and `Idempotency-Key`. See ADR-008.
- [Remove SSO configuration (owner only)](https://docs.mnemom.ai/api-reference/endpoint/delete-orgs-org-id-sso.md)
- [Delete webhook endpoint](https://docs.mnemom.ai/api-reference/endpoint/delete-orgs-org-id-webhooks-endpoint-id.md): Permanently delete a webhook endpoint and all its delivery history.
- [Archive team](https://docs.mnemom.ai/api-reference/endpoint/delete-teams-team-id.md): Archive a team. Archived teams are soft-deleted and can be listed with status=archived.
- [Remove member from team](https://docs.mnemom.ai/api-reference/endpoint/delete-teams-team-id-members-agent-id.md): Remove an agent from a team. Teams must retain a minimum of 2 members.
- [Delete transaction](https://docs.mnemom.ai/api-reference/endpoint/delete-transactions-id.md): Delete a guarded transaction. Only transactions in pending or completed status can be deleted. Active transactions must be completed or cancelled first.
- [List agents](https://docs.mnemom.ai/api-reference/endpoint/get-agents.md): List all agents owned by the authenticated user. Supports pagination.
- [Get agent by ID](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id.md)
- [List card amendments](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-card-amendments.md): Retrieve the history of all alignment card amendments for the specified agent. Card amendments are changes to the agent's alignment card that were triggered by reclassifications, policy changes, or manual edits.
- [Paginated integrity checkpoints](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-checkpoints.md)
- [Get single checkpoint](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-checkpoints-checkpoint-id.md)
- [Export compliance record](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-compliance-export.md): Export a comprehensive compliance record for the agent including all checkpoints, reclassifications, card amendments, and score history. Returns a structured document suitable for regulatory audits and compliance reviews.
- [Get conscience values for agent](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-conscience-values.md)
- [Get deletion status](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-deletion-status.md): Check the progress of a GDPR Article 17 deletion cascade
- [Get AIP drift alerts](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-drift-aip.md)
- [Get AIP enforcement mode](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-enforcement.md)
- [AIP integrity score](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-integrity-aip.md)
- [List reclassifications](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-reclassifications.md): Retrieve the history of all checkpoint reclassifications for the specified agent. Each entry includes the original and reclassified type, reason, and score impact.
- [List resolutions for an agent](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-resolutions.md)
- [Unified dual-rail AIP + AAP timeline](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-timeline.md)
- [Get traces for agent (AAP query alias)](https://docs.mnemom.ai/api-reference/endpoint/get-agents-agent-id-traces.md)
- [Get Merkle root](https://docs.mnemom.ai/api-reference/endpoint/get-agents-id-merkle-root.md): Get the current Merkle tree root for an agent. The root is a SHA-256 hash that commits to the complete set of integrity checkpoints for this agent. Public endpoint, no authentication required.
- [List active API keys](https://docs.mnemom.ai/api-reference/endpoint/get-api-keys.md)
- [Email-link landing (confirm / recovery / magic link)](https://docs.mnemom.ai/api-reference/endpoint/get-auth-callback.md): Handles Supabase-hosted email links. Verifies the token via GoTrue, issues `mnemom_session` when the flow returns tokens (signup confirm, magic link), or redirects without a session for recovery flows where the SPA performs the next step.
- [Get authenticated user info and linked agents](https://docs.mnemom.ai/api-reference/endpoint/get-auth-me.md)
- [List the current user's TOTP factors](https://docs.mnemom.ai/api-reference/endpoint/get-auth-mfa-factors.md)
- [List enrolled passkeys](https://docs.mnemom.ai/api-reference/endpoint/get-auth-passkeys.md): Returns the safe subset of `user_passkeys` for the authenticated user (omits public_key, counter, last_used_ip).
- [Cookie-aware whoami](https://docs.mnemom.ai/api-reference/endpoint/get-auth-session.md): Minimal whoami endpoint. Returns `{ user }` when the `mnemom_session` cookie is valid; returns 401 otherwise. Preferred over `GET /auth/me` for cookie-only browser sessions — `/auth/me` is bearer-only and preserves its legacy response shape unchanged.
- [IdP callback landing](https://docs.mnemom.ai/api-reference/endpoint/get-auth-sso-callback.md): Validates the HMAC-signed state (from the `mnemom_sso_initiator` cookie), consumes the single-use nonce, exchanges the PKCE code, enforces domain + org binding, performs SSO identity linking (T3-2c), and issues `mnemom_session` via a 302 to the SPA's `redirect_after` path.
- [Check if email domain has SSO enabled](https://docs.mnemom.ai/api-reference/endpoint/get-auth-sso-check-domain.md)
- [Get budget alert settings](https://docs.mnemom.ai/api-reference/endpoint/get-billing-budget-alert.md)
- [Export usage data as CSV](https://docs.mnemom.ai/api-reference/endpoint/get-billing-export-usage.md)
- [Get plan feature flags for authenticated user](https://docs.mnemom.ai/api-reference/endpoint/get-billing-features.md)
- [List invoices](https://docs.mnemom.ai/api-reference/endpoint/get-billing-invoices.md)
- [Get authenticated user billing summary](https://docs.mnemom.ai/api-reference/endpoint/get-billing-me.md)
- [Get current subscription details](https://docs.mnemom.ai/api-reference/endpoint/get-billing-subscription.md)
- [Get usage metrics for current user](https://docs.mnemom.ai/api-reference/endpoint/get-billing-usage.md)
- [Get per-agent usage breakdown](https://docs.mnemom.ai/api-reference/endpoint/get-billing-usage-agents.md)
- [Get author profile and their posts](https://docs.mnemom.ai/api-reference/endpoint/get-blog-authors-agent-id.md)
- [List published blog posts](https://docs.mnemom.ai/api-reference/endpoint/get-blog-posts.md)
- [Get single blog post by slug](https://docs.mnemom.ai/api-reference/endpoint/get-blog-posts-slug.md)
- [Get integrity certificate](https://docs.mnemom.ai/api-reference/endpoint/get-checkpoints-id-certificate.md): Retrieve or reconstruct the IntegrityCertificate for a checkpoint. Includes signature, chain proof, Merkle inclusion proof (if available), and verdict derivation proof (if completed). Public endpoint, no authentication required.
- [Get inclusion proof](https://docs.mnemom.ai/api-reference/endpoint/get-checkpoints-id-inclusion-proof.md): Generate and return a Merkle inclusion proof for a checkpoint. The proof contains O(log N) sibling hashes sufficient to recompute the Merkle root, proving the checkpoint is included in the agent's complete checkpoint history. Public endpoint, no authentication required.
- [Get proof status](https://docs.mnemom.ai/api-reference/endpoint/get-checkpoints-id-proof.md): Get the ZK proof status and data for a checkpoint. Returns the most recent proof record including status, proof type, verification result, and timing metadata. Public endpoint, no authentication required.
- [Get AAP drift alerts for agent](https://docs.mnemom.ai/api-reference/endpoint/get-drift-agent-id.md)
- [Compute AAP integrity score](https://docs.mnemom.ai/api-reference/endpoint/get-integrity-agent-id.md)
- [List signing keys](https://docs.mnemom.ai/api-reference/endpoint/get-keys.md): List all active Ed25519 signing public keys. Public endpoint, no authentication required. These keys are used to verify IntegrityCertificate signatures.
- [On-chain anchoring history](https://docs.mnemom.ai/api-reference/endpoint/get-on-chain-history.md): Retrieve the history of on-chain Merkle root anchoring events. Returns a paginated list of all anchors with their transaction details, included agents, and verification status.
- [On-chain anchoring status](https://docs.mnemom.ai/api-reference/endpoint/get-on-chain-status-agent-id.md): Get the current on-chain anchoring status for an agent. Returns the most recent anchor, pending publications, and overall on-chain coverage statistics.
- [Verify on-chain proof](https://docs.mnemom.ai/api-reference/endpoint/get-on-chain-verify-proof-agent-id.md): Verify an agent's integrity or score proof against the on-chain Merkle root. Checks that the provided proof correctly links the agent's data to an anchored root, confirming the data has not been tampered with since anchoring.
- [List organizations for authenticated user](https://docs.mnemom.ai/api-reference/endpoint/get-orgs.md)
- [Get organization details](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id.md)
- [List agents in organization](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-agents.md)
- [Get agent containment status](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-agents-agent-id-containment.md): Returns the current containment status and recent audit log entries. Any org role.
- [Get organization alignment template](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-alignment-template.md): Returns the org-level alignment template that is composed into every member agent's canonical card (between platform defaults and the agent's own card). Any org role (owner/admin/member/viewer/auditor) may read. Returns `template: null, enabled: false` if none is set. See ADR-008 (UC-4).
- [List organization API keys](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-api-keys.md)
- [Read the audit log](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-audit-log.md): Returns request-level audit entries scoped to this org: events made with an org-level API key, plus any event on a `/v1/orgs/{org_id}/...` URL. Excludes Mnemom-staff actions on `/v1/admin/*` paths. Compliance-shaped — `owner`, `admin`, and `auditor` roles only.
- [Get billing summary](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-billing-summary.md): Plan + customer-safe account state + 30-day usage rollup. Does **not** include invoice history (use `POST /orgs/{org_id}/billing/portal-session` for that) or recent billing events (the org audit log covers events generally). Internal Stripe identifiers and Mnemom-staff notes are scrubbed from the re…
- [List org conscience values](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-conscience-values.md): Returns all conscience values for the org, along with mode and enabled status. Requires Enterprise plan with custom_conscience_values feature flag.
- [Get conscience values audit log](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-conscience-values-log.md): Returns the audit trail for conscience value changes. Requires owner, admin, or auditor role.
- [Get organization cost rollup](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-costs.md): Daily usage broken down by model with a USD cost estimate per row plus aggregate totals. Cost figures are estimates derived from Mnemom's published per-model pricing applied to your actual token volume; authoritative billing is in Stripe (see `POST /orgs/{org_id}/billing/portal-session`). Billing-sh…
- [List pending invitations](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-invitations.md)
- [List organization members](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-members.md)
- [Get organization protection template](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-protection-template.md): Returns the org-level protection (Safe House) template composed into every member agent's canonical protection card. Any org role may read. See ADR-008 (UC-4).
- [Get SSO configuration for organization](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-sso.md)
- [List teams in organization](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-teams.md): List all teams belonging to an organization, filtered by status.
- [Get organization usage](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-usage.md): Operational usage metrics — request count plus token volume per day. Dashboard-shaped: visible to all org roles except viewer (members and auditors retain access for self-monitoring and compliance respectively). For dollar-cost rollups see `GET /orgs/{org_id}/costs`.
- [List webhook endpoints](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-webhooks.md): List all webhook endpoints for the organization. Signing secrets are not included.
- [Get webhook delivery log](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-webhooks-deliveries.md): Paginated delivery log for the organization. Optionally filter by endpoint_id.
- [Get webhook endpoint details](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-webhooks-endpoint-id.md): Get details for a single webhook endpoint. Signing secret is not included.
- [Get webhook delivery health](https://docs.mnemom.ai/api-reference/endpoint/get-orgs-org-id-webhooks-health.md): Returns active + disabled endpoint counts, 24-hour delivery counts (success / failed / total), success rate, and the top event types delivered in the last 24 hours. Useful for Status-page-style dashboards or monitoring integrations. Read-only: `owner`, `admin`, and `auditor`.
- [List public pricing plans](https://docs.mnemom.ai/api-reference/endpoint/get-plans.md)
- [Get traces with semantic similarity scores](https://docs.mnemom.ai/api-reference/endpoint/get-ssm-agent-id.md)
- [Get similarity timeline data](https://docs.mnemom.ai/api-reference/endpoint/get-ssm-agent-id-timeline.md)
- [Get team by ID](https://docs.mnemom.ai/api-reference/endpoint/get-teams-team-id.md): Retrieve a team and its current members.
- [Get team trust badge SVG](https://docs.mnemom.ai/api-reference/endpoint/get-teams-team-id-badge-svg.md): Public endpoint. Returns an SVG badge displaying the team's reputation score or grade. Returns a 'Not Rated' badge for unknown teams.
- [Get team alignment card](https://docs.mnemom.ai/api-reference/endpoint/get-teams-team-id-card.md): Retrieve the active alignment card for a team, or null if no card is set.
- [Get team card version history](https://docs.mnemom.ai/api-reference/endpoint/get-teams-team-id-card-history.md): Retrieve the history of alignment cards for a team.
- [Get team reputation score](https://docs.mnemom.ai/api-reference/endpoint/get-teams-team-id-reputation.md): Retrieve the current reputation score for a team, including component breakdown and A2A trust extension.
- [Get team reputation history](https://docs.mnemom.ai/api-reference/endpoint/get-teams-team-id-reputation-history.md): Retrieve weekly reputation score snapshots for a team.
- [Verify team reputation cryptographically](https://docs.mnemom.ai/api-reference/endpoint/get-teams-team-id-reputation-verify.md): Public endpoint. Returns the team's reputation score with a cryptographic proof hash for independent verification.
- [Get team roster history](https://docs.mnemom.ai/api-reference/endpoint/get-teams-team-id-roster-history.md): Retrieve the history of member additions and removals for a team.
- [Query traces with filters](https://docs.mnemom.ai/api-reference/endpoint/get-traces.md)
- [Get single trace by ID](https://docs.mnemom.ai/api-reference/endpoint/get-traces-trace-id.md)
- [Get transaction by ID](https://docs.mnemom.ai/api-reference/endpoint/get-transactions-id.md): Retrieve the details of a guarded transaction including its current status, policy evaluation result, and action outcomes.
- [Update organization](https://docs.mnemom.ai/api-reference/endpoint/patch-orgs-org-id.md)
- [Update org conscience value](https://docs.mnemom.ai/api-reference/endpoint/patch-orgs-org-id-conscience-values-value-id.md): Update fields on an existing conscience value. Requires owner or admin role.
- [Update member role (owner only)](https://docs.mnemom.ai/api-reference/endpoint/patch-orgs-org-id-members-user-id.md)
- [Update webhook endpoint](https://docs.mnemom.ai/api-reference/endpoint/patch-orgs-org-id-webhooks-endpoint-id.md): Update an existing webhook endpoint. Re-enabling a disabled endpoint resets the failure counter.
- [Update team](https://docs.mnemom.ai/api-reference/endpoint/patch-teams-team-id.md): Update a team's name, description, or metadata.
- [Register agent](https://docs.mnemom.ai/api-reference/endpoint/post-agents.md): Register a new agent with a name and hash proof. Optionally attach an alignment card and policy.
- [Claim agent with hash proof](https://docs.mnemom.ai/api-reference/endpoint/post-agents-agent-id-claim.md)
- [Link claimed agent to authenticated user](https://docs.mnemom.ai/api-reference/endpoint/post-agents-agent-id-link.md)
- [Reclassify a checkpoint](https://docs.mnemom.ai/api-reference/endpoint/post-agents-agent-id-reclassify.md): Reclassify a previously recorded AIP checkpoint violation. This allows operators to correct false positives or adjust severity after manual review. The reclassification is recorded in the audit trail and can trigger a score recomputation.
- [Re-bind agent to a new API key](https://docs.mnemom.ai/api-reference/endpoint/post-agents-agent-id-rekey.md): Updates the agent's key binding to a new provider API key hash. The agent ID, traces, alignment card, integrity score, and trust edges are fully preserved.
- [Resolve a concern or violation](https://docs.mnemom.ai/api-reference/endpoint/post-agents-agent-id-resolve.md)
- [Re-verify AAP traces against updated card](https://docs.mnemom.ai/api-reference/endpoint/post-agents-agent-id-reverify.md)
- [Re-evaluate AIP checkpoints against updated card](https://docs.mnemom.ai/api-reference/endpoint/post-agents-agent-id-reverify-aip.md)
- [Verify key binding](https://docs.mnemom.ai/api-reference/endpoint/post-agents-agent-id-verify-binding.md): Checks whether a given API key hash matches the key currently bound to this agent. The raw key is hashed client-side — only the hash is transmitted.
- [Register AIP webhook](https://docs.mnemom.ai/api-reference/endpoint/post-aip-webhooks.md)
- [Run single integrity analysis](https://docs.mnemom.ai/api-reference/endpoint/post-analyze.md)
- [Run batch integrity analysis (1-50 items)](https://docs.mnemom.ai/api-reference/endpoint/post-analyze-batch.md)
- [Create a personal API key](https://docs.mnemom.ai/api-reference/endpoint/post-api-keys.md)
- [Rotate a personal API key](https://docs.mnemom.ai/api-reference/endpoint/post-api-keys-key-id-rotate.md): Atomically mints a replacement key with the same `name` and `scopes` as the original, then immediately revokes the old key. The full new secret is returned in the response — this is your only chance to capture it. Old key is invalid as soon as the response is returned; if you need overlap with an in…
- [Exchange a cookie session for raw Supabase tokens](https://docs.mnemom.ai/api-reference/endpoint/post-auth-cli-exchange.md): One-shot endpoint called by the SPA during the CLI login flow (browser → localhost handoff). Requires a valid `mnemom_session`. Returns access + refresh tokens in the JSON body. Does not modify cookies.
- [CLI password login — returns bearer tokens](https://docs.mnemom.ai/api-reference/endpoint/post-auth-login.md): Legacy CLI-targeted endpoint. Unlike `/auth/sign-in`, this does NOT set cookies — it returns Supabase access + refresh tokens in the JSON body for the CLI to persist at `~/.mnemom/auth.json`. Rate-limited.
- [Issue a challenge for a TOTP factor](https://docs.mnemom.ai/api-reference/endpoint/post-auth-mfa-challenge.md): Called during the sign-in MFA step-up flow (using the `mnemom_mfa_pending` cookie) or during enrollment verification (using the existing `mnemom_session`). Returns a `challenge_id` to pass to `/auth/mfa/verify`.
- [Enroll a new TOTP factor](https://docs.mnemom.ai/api-reference/endpoint/post-auth-mfa-enroll.md): Returns the TOTP secret + provisioning URI for a QR code. Factor starts in `unverified` state until `/auth/mfa/verify` is called against it.
- [Unenroll a TOTP factor](https://docs.mnemom.ai/api-reference/endpoint/post-auth-mfa-unenroll.md): Requires an aal2 session (freshly MFA-verified). Returns 403 `code: aal2_required` if the session isn't aal2.
- [Complete MFA step-up or enrollment](https://docs.mnemom.ai/api-reference/endpoint/post-auth-mfa-verify.md): Sign-in flow: consumes the `mnemom_mfa_pending` cookie, verifies the TOTP code, and issues a full `mnemom_session`. Enrollment flow: verifies a freshly-enrolled factor using the current session and upgrades it to aal2.
- [Begin passkey sign-in — return WebAuthn assertion options](https://docs.mnemom.ai/api-reference/endpoint/post-auth-passkey-challenge.md): Unauthenticated. Returns `PublicKeyCredentialRequestOptions` with an empty `allowCredentials` list (discoverable-credentials flow). The browser surfaces any matching passkey for this RP without needing the user to enter an email. Rate-limited.
- [Begin passkey enrollment — return WebAuthn creation options](https://docs.mnemom.ai/api-reference/endpoint/post-auth-passkey-enroll.md): Authenticated endpoint. Returns `PublicKeyCredentialCreationOptions` for the SPA to pass to `navigator.credentials.create()`. Stores the challenge in KV with a 30-second TTL; the companion `/verify-enroll` endpoint consumes it. `excludeCredentials` is pre-populated with the user's existing passkeys…
- [Verify passkey assertion and issue a session](https://docs.mnemom.ai/api-reference/endpoint/post-auth-passkey-verify-auth.md): Unauthenticated. Consumes the challenge issued by `/auth/passkey/challenge`, verifies the assertion via `@simplewebauthn/server`, mints Supabase tokens via `admin.generateLink(magiclink)` for the resolved user (same pattern T3-2c uses for SSO identity linking), and issues `mnemom_session` with `auth…
- [Verify passkey registration + persist the credential](https://docs.mnemom.ai/api-reference/endpoint/post-auth-passkey-verify-enroll.md): Authenticated endpoint. Consumes the challenge issued by `/auth/passkey/enroll`, verifies the attestation via `@simplewebauthn/server`, and inserts a row into `user_passkeys`. A user-supplied `friendly_name` is stored alongside for UI display.
- [Request a password reset email](https://docs.mnemom.ai/api-reference/endpoint/post-auth-password-reset-request.md): Always returns 200 on 4xx upstream responses (to avoid user enumeration). 5xx upstream errors surface as 5xx to the caller.
- [CLI token refresh](https://docs.mnemom.ai/api-reference/endpoint/post-auth-refresh.md): Legacy CLI-targeted refresh grant. Trades a refresh token for a new access + refresh token pair. Rate-limited.
- [Resend email confirmation](https://docs.mnemom.ai/api-reference/endpoint/post-auth-resend-confirmation.md): Re-sends the signup confirmation email for a pending account.
- [Sign in with email + password](https://docs.mnemom.ai/api-reference/endpoint/post-auth-sign-in.md): Server-enforces SSO for org-enforced domains (returns 403 with `code: sso_required`). For users with a verified TOTP factor, returns 200 `{ mfa_required: true, factor_id }` and sets a short-lived `mnemom_mfa_pending` cookie; otherwise issues `mnemom_session` and returns `{ user }`.
- [Sign out and clear session cookies](https://docs.mnemom.ai/api-reference/endpoint/post-auth-sign-out.md): Revokes the refresh token upstream and clears `mnemom_session` + `mnemom_mfa_pending`.
- [Sign up with email + password](https://docs.mnemom.ai/api-reference/endpoint/post-auth-sign-up.md): Creates a new user account. When email confirmation is required on the Supabase project, returns `{ user, email_confirmation_required: true }` without issuing a session cookie; the user must click the email link. When auto-confirm is on, issues `mnemom_session` and returns `{ user }`.
- [Begin an SSO login flow](https://docs.mnemom.ai/api-reference/endpoint/post-auth-sso-initiate.md): Looks up the SSO provider for the email's domain, generates PKCE + HMAC-signed state, sets a short-lived `mnemom_sso_initiator` cookie, and returns the IdP URL for the SPA to `window.location.href` to.
- [Cancel subscription at period end](https://docs.mnemom.ai/api-reference/endpoint/post-billing-cancel.md)
- [Change subscription plan](https://docs.mnemom.ai/api-reference/endpoint/post-billing-change-plan.md)
- [Create Stripe checkout session](https://docs.mnemom.ai/api-reference/endpoint/post-billing-checkout.md)
- [Create Stripe billing portal session](https://docs.mnemom.ai/api-reference/endpoint/post-billing-portal.md)
- [Reactivate a subscription scheduled for cancellation](https://docs.mnemom.ai/api-reference/endpoint/post-billing-reactivate.md)
- [Validate a promo code](https://docs.mnemom.ai/api-reference/endpoint/post-billing-validate-promo.md)
- [Create blog post (service role only)](https://docs.mnemom.ai/api-reference/endpoint/post-blog-posts.md): **Requires ServiceRole authentication.** This endpoint is only accessible to platform administrators with the Supabase service role key. Regular API keys and user tokens cannot access this endpoint.
- [Request ZK proof](https://docs.mnemom.ai/api-reference/endpoint/post-checkpoints-id-prove.md): Request a zero-knowledge proof for a checkpoint's verdict derivation. If a proof already exists, returns its current status. Otherwise, creates a pending proof request and dispatches it to the SP1 prover service. Requires API key authentication.
- [Submit enterprise contact form](https://docs.mnemom.ai/api-reference/endpoint/post-enterprise-contact.md)
- [Validate a license key (public)](https://docs.mnemom.ai/api-reference/endpoint/post-license-validate.md)
- [Create organization](https://docs.mnemom.ai/api-reference/endpoint/post-orgs.md)
- [Accept an organization invitation](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-invitations-accept.md)
- [Kill an agent](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-agents-agent-id-kill.md): Permanently stop an agent. Requires explicit reactivation to restore. Owner only.
- [Pause an agent](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-agents-agent-id-pause.md): Temporarily stop an agent from making API requests. Requires owner or admin role.
- [Reactivate a killed agent](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-agents-agent-id-reactivate.md): Restore a killed agent back to active state. Owner only.
- [Resume a paused agent](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-agents-agent-id-resume.md): Resume a paused agent back to active state. Only works on paused agents. Requires owner or admin role.
- [Create organization API key](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-api-keys.md)
- [Rotate an organization API key](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-api-keys-key-id-rotate.md): Atomic mint-new + immediately-revoke-old, with the same `name` and `scopes` as the original. The full new secret is returned only in this response. No grace period — old key is invalid immediately. If you need overlap with an in-flight deploy, create a second key first via `POST /orgs/{org_id}/api-k…
- [Open the Stripe Customer Portal](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-billing-portal-session.md): Mints a single-use URL into Stripe's hosted Customer Portal where the org admin can view invoices, download PDFs, update payment methods, change billing details, and manage their subscription. The portal is the primary surface for invoice access — there is no direct invoice API. `owner` and `admin`…
- [Create org conscience value](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-conscience-values.md): Create a new custom conscience value. Max 20 per org. Requires owner or admin role.
- [Invite member to organization](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-invitations.md)
- [Enable Safe House for an organization](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-safe-house-enable.md): Customer-admin entry point to set the Safe House mode for an organization. Mirrors the staff-only `POST /v1/admin/safe-house/enable` route; both call the same `enable_sh_for_org(p_org_id, p_mode)` RPC. Caller must be an `owner` or `admin` of the target org.
- [Test SSO metadata URL validity](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-sso-test.md)
- [Create webhook endpoint](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-webhooks.md): Create a new webhook endpoint for the organization. Returns the signing secret (shown only once). Maximum 5 endpoints per organization.
- [Redeliver a webhook event](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-webhooks-deliveries-delivery-id-redeliver.md): Create a new delivery attempt for a previously failed event. A new delivery row is created with next_attempt_at set to now.
- [Rotate webhook signing secret](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-webhooks-endpoint-id-rotate-secret.md): Generate a new signing secret for the endpoint. The new secret is returned once. Previous secret is immediately invalidated.
- [Send test webhook delivery](https://docs.mnemom.ai/api-reference/endpoint/post-orgs-org-id-webhooks-endpoint-id-test.md): Send a synchronous test delivery to the endpoint with a synthetic webhook.test event. Returns the delivery result immediately.
- [Evaluate policy](https://docs.mnemom.ai/api-reference/endpoint/post-policies-evaluate.md): Evaluate a CLPI policy against a list of tools to determine which are allowed, forbidden, or unmapped. Returns a verdict with detailed violations, warnings, card coverage gaps, and overall coverage percentage. Useful for dry-run validation before deploying a policy.
- [Evaluate policy against history](https://docs.mnemom.ai/api-reference/endpoint/post-policies-evaluate-historical.md): Evaluate a CLPI policy against historical AIP traces for an agent. Replays past tool invocations through the policy to identify what would have been blocked, escalated, or flagged. Useful for understanding the impact of a policy change before rolling it out.
- [Recompute reputation score](https://docs.mnemom.ai/api-reference/endpoint/post-reputation-agent-id-recompute.md): Trigger a full recomputation of the agent's reputation and compliance scores. This re-evaluates all checkpoints, reclassifications, and card amendments to produce an updated score. Useful after bulk reclassifications or policy changes.
- [Create a team](https://docs.mnemom.ai/api-reference/endpoint/post-teams.md): Create a new team with at least 2 agent members. Team names must be unique within the organization.
- [Extract team fault lines](https://docs.mnemom.ai/api-reference/endpoint/post-teams-fault-lines.md): Analyze alignment fault lines across a team of agents. Identifies capabilities, values, or constraints that some agents declare but others miss, creating potential alignment gaps. Returns a fleet-wide score with individual fault line details and resolution hints.
- [Forecast team risks](https://docs.mnemom.ai/api-reference/endpoint/post-teams-forecast.md): Forecast potential risks and failure modes for a team based on current alignment state, historical trends, and known fault lines. Returns ranked failure modes with probability estimates, impact assessments, and mitigation suggestions.
- [Recommend team policy](https://docs.mnemom.ai/api-reference/endpoint/post-teams-recommend-policy.md): Generate a recommended CLPI policy for a team based on current agent capabilities, alignment cards, historical violations, and known fault lines. The recommendation aims to close coverage gaps while minimizing disruption to existing workflows.
- [Derive team card from member cards](https://docs.mnemom.ai/api-reference/endpoint/post-teams-team-id-card-derive.md): Automatically derive a team alignment card from the individual cards of team members. Requires at least 2 members with active alignment cards.
- [Add members to team](https://docs.mnemom.ai/api-reference/endpoint/post-teams-team-id-members.md): Add one or more agents to a team. Teams have a maximum of 50 members.
- [Create transaction](https://docs.mnemom.ai/api-reference/endpoint/post-transactions.md): Create a new guarded transaction. The transaction wraps one or more agent actions with CLPI policy guardrails, ensuring all tool invocations are evaluated against the effective policy before execution. Returns the transaction ID and initial evaluation status.
- [Verify certificate](https://docs.mnemom.ai/api-reference/endpoint/post-verify.md): Verify an IntegrityCertificate. Performs Ed25519 signature verification, chain hash verification, Merkle inclusion proof verification, input commitment check, and optional STARK proof verification. Public endpoint, no authentication required.
- [Update agent](https://docs.mnemom.ai/api-reference/endpoint/put-agents-agent-id.md): Update the name of an agent you own.
- [Update conscience values](https://docs.mnemom.ai/api-reference/endpoint/put-agents-agent-id-conscience-values.md)
- [Update AIP enforcement mode](https://docs.mnemom.ai/api-reference/endpoint/put-agents-agent-id-enforcement.md)
- [Set budget alert threshold](https://docs.mnemom.ai/api-reference/endpoint/put-billing-budget-alert.md)
- [Update auto-containment policy](https://docs.mnemom.ai/api-reference/endpoint/put-orgs-org-id-agents-agent-id-containment-policy.md): Set or disable the auto-containment threshold. When set, the agent will be automatically paused after N consecutive boundary violations. Requires owner or admin role.
- [Set organization alignment template](https://docs.mnemom.ai/api-reference/endpoint/put-orgs-org-id-alignment-template.md): Requires org `owner` or `admin`. Accepts YAML or JSON. Body cap: 128 KiB. The first PUT auto-enables the template; subsequent PUTs leave `enabled` unchanged unless explicitly overridden. Every member agent is flagged for canonical recompose. Requires `Idempotency-Key`. See ADR-008.
- [Update org conscience mode](https://docs.mnemom.ai/api-reference/endpoint/put-orgs-org-id-conscience-values-mode.md): Set the conscience mode (augment/replace) and enabled flag.
- [Reorder org conscience values](https://docs.mnemom.ai/api-reference/endpoint/put-orgs-org-id-conscience-values-order.md): Set the sort order for all conscience values.
- [Set organization protection template](https://docs.mnemom.ai/api-reference/endpoint/put-orgs-org-id-protection-template.md): Requires org `owner`/`admin`. Body cap: 64 KiB. Every member agent is flagged for canonical recompose. Requires `Idempotency-Key`. See ADR-008.
- [Configure SAML SSO for organization (owner only)](https://docs.mnemom.ai/api-reference/endpoint/put-orgs-org-id-sso.md)
- [Set team alignment card](https://docs.mnemom.ai/api-reference/endpoint/put-teams-team-id-card.md): Manually set an alignment card for a team. The card must include principal, values, autonomy_envelope, and audit_commitment sections.
- [Governance guarantees](https://docs.mnemom.ai/api-reference/governance.md): Cross-cutting contracts that apply to every card, template, and exemption mutation — audit, idempotency, schema identity, webhooks.
- [Intelligence API](https://docs.mnemom.ai/api-reference/intelligence-overview.md): API reference for fault line analysis, risk forecasting, policy recommendations, and transaction guardrails
- [On-Chain API](https://docs.mnemom.ai/api-reference/on-chain-overview.md): API reference for on-chain Merkle root anchoring, score publishing, and verification on Base L2
- [API Reference Overview](https://docs.mnemom.ai/api-reference/overview.md): Authentication, base URL, error handling, and rate limits for the Mnemom API
- [Policy API](https://docs.mnemom.ai/api-reference/policy-overview.md): API reference for policy management — CRUD, evaluation, and resolved policy retrieval
- [Reclassification API](https://docs.mnemom.ai/api-reference/reclassification-overview.md): API reference for violation reclassification, score recomputation, card amendments, and compliance export
- [Mnemom Trust Rating API](https://docs.mnemom.ai/api-reference/reputation-overview.md): Complete API reference for the Mnemom Trust Rating™ — score retrieval, history, badges, batch lookup, directory search, comparison, and benchmarks.
- [Risk API](https://docs.mnemom.ai/api-reference/risk-overview.md): API reference for individual and team risk assessment endpoints
- [Safe House API Reference](https://docs.mnemom.ai/api-reference/safe-house-overview.md): Complete reference for all Safe House endpoints — configuration, quarantine management, observability, pattern library, canary credentials, and compliance.
- [Teams API](https://docs.mnemom.ai/api-reference/team-overview.md): Complete API reference for team CRUD, alignment cards, reputation, and badges
- [Unified cards](https://docs.mnemom.ai/api-reference/unified-cards-overview.md): The alignment and protection card surface — what each card is, how they compose, and where to find each endpoint.
- [Changelog](https://docs.mnemom.ai/changelog.md): Release history and updates for Mnemom protocols and infrastructure
- [Agent Cards](https://docs.mnemom.ai/concepts/agent-cards.md): Every Mnemom agent has two cards — an alignment card (who the agent is and what it's allowed to do) and a protection card (how it's defended). Both are YAML, both compose across three scopes.
- [Agent Identity](https://docs.mnemom.ai/concepts/agent-identity.md): How agents are identified in Mnemom, the ID formats in use, and what you can rely on.
- [Alignment Cards](https://docs.mnemom.ai/concepts/alignment-cards.md): Declarative specifications of an AI agent's intended values, boundaries, and behavioral commitments
- [AP-Traces](https://docs.mnemom.ai/concepts/ap-traces.md): Structured records of agent actions for post-hoc alignment verification
- [Card Composition](https://docs.mnemom.ai/concepts/card-composition.md): How alignment and protection cards compose across platform > org > agent scope, with field-level rules, exemptions, and canonical-card semantics.
- [Card Lifecycle](https://docs.mnemom.ai/concepts/card-lifecycle.md): How alignment cards evolve as living artifacts — amendments, reclassification, trust recovery, and version tracking
- [CLPI: Card Lifecycle & Policy Intelligence](https://docs.mnemom.ai/concepts/clpi.md): The governance layer that transforms alignment cards into lifecycle-managed artifacts with policy enforcement, trust recovery, risk intelligence, and on-chain anchoring
- [Drift Detection](https://docs.mnemom.ai/concepts/drift-detection.md): Detecting when AI agent behavior diverges from declared alignment over time
- [Fleet Coherence](https://docs.mnemom.ai/concepts/fleet-coherence.md): Dimensional team coherence scoring — governance, conflict surface, structural invariants, and narrative helpers. No single fleet score.
- [Integrity Checkpoints](https://docs.mnemom.ai/concepts/integrity-checkpoints.md): Real-time analysis of LLM reasoning to detect prompt injection, manipulation, and drift
- [On-Chain Verification](https://docs.mnemom.ai/concepts/on-chain-verification.md): Immutable reputation anchoring on Base L2 via ERC-8004 smart contracts — Merkle root anchoring, score publishing, and cryptographic verification
- [Policy Engine](https://docs.mnemom.ai/concepts/policy-engine.md): Governance-as-code: capability mappings, forbidden rules, and enforcement modes, all declared in the alignment card's capabilities + enforcement sections
- [Protection Card](https://docs.mnemom.ai/concepts/protection-card.md): The YAML document that tells Safe House how to defend an agent at runtime. Mode, thresholds, screen surfaces, trusted sources — all edited, composed, and audited like an alignment card.
- [Mnemom Trust Rating](https://docs.mnemom.ai/concepts/reputation-scores.md): The Mnemom Trust Rating™ — a credit score for AI agents. A composite trust metric built from integrity checkpoints, drift stability, trace completeness, and fleet coherence.
- [Risk Assessment](https://docs.mnemom.ai/concepts/risk-assessment.md): Context-aware, real-time risk scoring for individual agents and teams — with optional zero-knowledge proofs
- [Safe House](https://docs.mnemom.ai/concepts/safe-house.md): Pre-screening layer that evaluates every inbound message before it reaches your AI agent — blocking prompt injections, social engineering, and data exfiltration attempts before they cause harm
- [Team Trust Rating](https://docs.mnemom.ai/concepts/team-reputation.md): The Team Trust Rating — a composite trust metric for teams of AI agents. Built from coherence history, member quality, operational record, structural stability, and assessment density.
- [Value Coherence](https://docs.mnemom.ai/concepts/value-coherence.md): Pairwise verification that interacting AI agents share compatible values
- [Whitepaper](https://docs.mnemom.ai/concepts/whitepaper.md): Mnemom as the trust plane for agentic systems — the unified composition of AAP, AIP, Safe House, and cryptographic attestation behind the managed gateway
- [For AI Agents](https://docs.mnemom.ai/for-agents/index.md): If you're an AI agent reading Mnemom's docs to help your operator integrate — start here. Written in second person, optimized for the fastest path from zero to integrated.
- [CLI Reference](https://docs.mnemom.ai/gateway/cli.md): Mnemom CLI commands and usage
- [Custom Conscience Values](https://docs.mnemom.ai/gateway/conscience-values.md): Per-org alignment policies injected into the AIP conscience prompt
- [Enforcement Modes](https://docs.mnemom.ai/gateway/enforcement.md): Configure how the Mnemom Gateway responds to alignment and integrity violations
- [Organization Card Templates](https://docs.mnemom.ai/gateway/org-card-templates.md): Define alignment card policies that apply to all agents in your organization
- [Mnemom Gateway Overview](https://docs.mnemom.ai/gateway/overview.md): Transparent AI agent tracing gateway with AAP and AIP compliance
- [Policy Commands (Moved)](https://docs.mnemom.ai/gateway/policy-cli.md): Policy management is now part of the alignment card. Use mnemom card evaluate for policy evaluation.
- [Safe House Gateway Integration](https://docs.mnemom.ai/gateway/safe-house-overview.md): How Safe House integrates with the Mnemom gateway request pipeline — phases, caching, AIP enrichment, and attestation
- [Rotating Your Agent's API Key](https://docs.mnemom.ai/guides/agent-key-rotation.md): How to update an agent's provider key binding without losing history
- [API Keys](https://docs.mnemom.ai/guides/api-keys.md): Personal vs. organization keys, when to use which, and how to rotate.
- [API Versioning](https://docs.mnemom.ai/guides/api-versioning.md): How to pin your integration to a specific API version and manage upgrades safely.
- [Managing Card Composition](https://docs.mnemom.ai/guides/card-composition.md): Practical guide: manage org templates, grant exemptions, inspect canonical cards, and debug composition across the platform > org > agent hierarchy.
- [Alignment Card Management](https://docs.mnemom.ai/guides/card-management.md): Create, validate, publish, and manage alignment cards for your AI agents
- [CI/CD Policy Gates](https://docs.mnemom.ai/guides/ci-cd-policy-gates.md): Integrate policy validation and evaluation into your CI/CD pipeline with GitHub Actions and GitLab CI
- [EU AI Act Compliance](https://docs.mnemom.ai/guides/eu-compliance.md): Article 50 transparency obligation mapping for AAP and AIP protocols
- [Fault Line Analysis](https://docs.mnemom.ai/guides/fault-line-analysis.md): Identify, classify, and resolve value misalignments in multi-agent teams. Fault-line classification runs alongside v2 coherence scoring and produces an actionable triage list.
- [GDPR Data Subject Rights](https://docs.mnemom.ai/guides/gdpr-data-subject-rights.md): Right to erasure (Article 17) — how Mnemom handles agent deletion requests
- [Improving Your Mnemom Trust Rating](https://docs.mnemom.ai/guides/improving-reputation.md): A practical guide to building, monitoring, and recovering your Mnemom Trust Rating™ — component-by-component strategies for agent builders and operators.
- [Migrating to Unified Cards](https://docs.mnemom.ai/guides/migrating-to-unified-cards.md): What changed in the UC migration, what the automatic data migration did for you, which legacy endpoints and fields are gone, and how to verify your agents are on the unified model.
- [Multi-Agent Setup](https://docs.mnemom.ai/guides/multi-agent-setup.md): Configure multiple agents with Alignment Cards, run coherence checks, and monitor fleet alignment.
- [Observability with OpenTelemetry](https://docs.mnemom.ai/guides/observability.md): OpenTelemetry exporter for AIP integrity checkpoints and AAP verification results
- [On-Chain Verification](https://docs.mnemom.ai/guides/on-chain-verification.md): Verify agent and team reputation scores, inspect Merkle anchors, and audit the on-chain trail — all via read-only Mnemom API calls or direct Base L2 RPC.
- [Org Admin](https://docs.mnemom.ai/guides/org-admin.md): What an organization owner or admin can do, the roles in your org, and how to escalate the things this surface deliberately doesn't cover.
- [Passkeys](https://docs.mnemom.ai/guides/passkeys.md): Sign in to Mnemom with a single biometric gesture — no password, no TOTP code. Passkeys use the WebAuthn standard and sync across your devices via iCloud Keychain, Google Password Manager, or 1Password.
- [Policy Management](https://docs.mnemom.ai/guides/policy-management.md): Create, test, publish, and manage governance policies for your AI agents
- [Embeddable Trust Badges](https://docs.mnemom.ai/guides/reputation-badges.md): Add trust signals to your README, website, Agent Card, or documentation with dynamic SVG badges showing your agent's Mnemom Trust Rating™.
- [Risk Engine](https://docs.mnemom.ai/guides/risk-engine.md): How to assess, gate, and monitor risk for individual agents and teams using the Mnemom Risk Engine
- [Protection Card Management](https://docs.mnemom.ai/guides/safe-house-config.md): Author, publish, validate, and tune the protection card that configures Safe House for an agent.
- [Safe House Monitoring](https://docs.mnemom.ai/guides/safe-house-monitoring.md): Monitor Safe House in production — the Security Observatory, key metrics, session escalation, campaign detection, pattern promotion, and evaluation history queries.
- [Safe House Threat Model](https://docs.mnemom.ai/guides/safe-house-threat-model.md): What Safe House protects against — specific attack vectors, detection mechanisms, known limits, and false positive management.
- [Safe House Webhooks](https://docs.mnemom.ai/guides/safe-house-webhooks.md): Receive real-time HTTP POST notifications for Safe House evaluation events — block decisions, quarantine alerts, canary triggers, and campaign detection.
- [Security & Trust Model](https://docs.mnemom.ai/guides/security-trust-model.md): How Mnemom handles data, authentication, encryption, and threat modeling across the alignment infrastructure.
- [Supply Chain Trust](https://docs.mnemom.ai/guides/supply-chain-trust.md): How Mnemom publishes its npm packages with SLSA provenance, and how to verify the packages you install.
- [Team Management](https://docs.mnemom.ai/guides/team-management.md): Create teams, manage rosters, derive alignment cards, and monitor team reputation
- [Trust Recovery](https://docs.mnemom.ai/guides/trust-recovery.md): Recover agent trust scores by reclassifying card-gap violations and amending alignment cards
- [Upgrading to AAP 0.5.0](https://docs.mnemom.ai/guides/upgrading-to-0-5.md): Step-by-step migration guide for updating your agents, cards, and policies to AAP 0.5.0
- [Upgrading to AAP & AIP 1.0.0](https://docs.mnemom.ai/guides/upgrading-to-1-0.md): Step-by-step migration from the 0.x series to the 1.0.0 stability commitment release.
- [Webhook Notifications](https://docs.mnemom.ai/guides/webhooks.md): Real-time HTTP POST notifications for integrity and alignment trace events — pipe violations, drift, conscience escalations, trace verification, and billing events into your ops stack.
- [WEF Agent Governance Framework](https://docs.mnemom.ai/guides/wef-governance.md): Mapping AAP and AIP to the World Economic Forum's AI agent governance framework
- [Introduction](https://docs.mnemom.ai/introduction.md): The trust plane for the agentic internet — transparent alignment verification, behavioral drift detection, and accountability protocols
- [Pricing & Plans](https://docs.mnemom.ai/pricing/overview.md): Transparent pricing for the trust plane
- [A2A Integration Guide](https://docs.mnemom.ai/protocols/aap/a2a-integration.md): How to extend A2A Agent Cards with AAP alignment properties for value coherence checks before agent-to-agent coordination
- [AAP Architecture](https://docs.mnemom.ai/protocols/aap/architecture.md): System architecture of the Agent Alignment Protocol including component relationships, data flow, and extension points
- [AAP Calibration Methodology](https://docs.mnemom.ai/protocols/aap/calibration.md): How AAP's drift detection thresholds were empirically derived from multi-turn agent conversation analysis
- [AAP Limitations and Honest Claims](https://docs.mnemom.ai/protocols/aap/limitations.md): What the Agent Alignment Protocol does and does not provide -- normative limitations that implementers must communicate
- [Adding AAP to MCP Tools](https://docs.mnemom.ai/protocols/aap/mcp-migration.md): How to extend MCP tools and servers with AAP alignment properties for alignment verification of tool invocations
- [AAP Quick Start Guide](https://docs.mnemom.ai/protocols/aap/quickstart.md): Get your agent producing verifiable alignment traces in 5 minutes
- [Mnemom Trust Rating™ Methodology](https://docs.mnemom.ai/protocols/aap/reputation-methodology.md): Normative specification for the Mnemom Trust Rating™ algorithm — composite formula, component definitions, confidence levels, and anti-gaming measures.
- [AAP Security Model](https://docs.mnemom.ai/protocols/aap/security.md): Security model for the Agent Alignment Protocol including threat analysis, cryptographic requirements, and defense in depth
- [AAP Specification](https://docs.mnemom.ai/protocols/aap/specification.md): Full protocol specification for the Agent Alignment Protocol (AAP) v0.1.0
- [Integrity Certificates](https://docs.mnemom.ai/protocols/aip/certificates.md): Machine-readable cryptographic certificates that bundle all verification evidence for an integrity checkpoint into a single, self-describing document.
- [AIP Limitations](https://docs.mnemom.ai/protocols/aip/limitations.md): What AIP does and does not do -- read before depending on AIP for anything consequential
- [AIP Quickstart](https://docs.mnemom.ai/protocols/aip/quickstart.md): Get from zero to real-time integrity checking in 5 minutes
- [AIP Security Model](https://docs.mnemom.ai/protocols/aip/security.md): Threat model and security considerations for the Agent Integrity Protocol
- [Agent Integrity Protocol (AIP) Specification](https://docs.mnemom.ai/protocols/aip/specification.md): Complete protocol specification for real-time integrity assurance of autonomous agents via thinking block analysis
- [Verifiable Verdicts](https://docs.mnemom.ai/protocols/aip/verifiable-verdicts.md): Zero-knowledge proofs for verdict derivation, enabling cryptographic verification that an integrity verdict was computed correctly from its inputs.
- [Protocol Overview](https://docs.mnemom.ai/protocols/overview.md): Understanding AAP, AIP, and CLPI — the protocol stack for agent trust
- [Mnemom Gateway Quickstart](https://docs.mnemom.ai/quickstart/gateway.md): Complete agent governance — verification, integrity analysis, and policy enforcement — in 5 minutes with zero code changes
- [Quickstart Overview](https://docs.mnemom.ai/quickstart/overview.md): Choose the right integration path for your AI agents
- [Enable Safe House Protection](https://docs.mnemom.ai/quickstart/safe-house-protection.md): Add pre-screening threat detection to an AI agent in 5 minutes — from observe mode through your first quarantined message
- [SDK Direct Integration](https://docs.mnemom.ai/quickstart/sdk-direct.md): Integrate alignment verification, integrity checking, and policy governance directly into your application
- [Self-Hosted Deployment](https://docs.mnemom.ai/quickstart/self-hosted.md): Run the Mnemom Gateway on your own infrastructure with Docker or Kubernetes
- [Alignment Card Schema](https://docs.mnemom.ai/specifications/alignment-card-schema.md): Normative YAML schema for the unified alignment card, including every section, field type, required/optional status, and composition semantic.
- [OpenTelemetry Attributes](https://docs.mnemom.ai/specifications/otel-attributes.md): Complete reference for AIP/AAP OTel span attributes and metrics
- [Policy DSL Specification](https://docs.mnemom.ai/specifications/policy-dsl.md): Normative schema definition for Mnemom Policy YAML — capability mappings, forbidden rules, escalation triggers, and defaults
- [Protection Card Schema](https://docs.mnemom.ai/specifications/protection-card-schema.md): Normative YAML schema for the protection card, including every section, field type, required/optional status, and composition semantic.

## OpenAPI Specs

- [openapi](https://docs.mnemom.ai/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/mnemom)
- [Blog](https://mnemom.ai/blog)