mnemom.ai

Acknowledge a governance signal — Records the actor + timestamp on the signal row.

Assign a posture to a team — Sets the team's active posture.

Claim a verifiable identity — bind an agent to your organization so its trust and accountability record is provably yours.

Clone a posture into an org — Copies the posture and its current revision into the target org's scope.

Create a personal API key — Mints a new personal API key.

Create a notification destination — Authorized: org_admin or org_owner.

Create an escalation rule — Authorized: org_admin or org_owner.

Create a posture — Authorized: org_admin / org_owner for org-scope; platform admins for platform-scope.

Create a webhook endpoint — Create a new webhook endpoint for the organization.

Delete a notification destination — Authorized: org_admin or org_owner.

Delete an escalation rule — Authorized: org_admin or org_owner.

Soft-delete a posture — Sets deleted_at; revisions retained for audit.

Delete webhook endpoint — Permanently delete a webhook endpoint and all its delivery history.

Structural diff between two revisions

Dismiss a governance signal as not actionable

Bind one of your agents to a Dojo Try-Me config so it can spar in the Dojo — links the agent to the config by id.

Look up an agent's public identity and trust state by ID — the accountable record other agents and humans can rely on.

Get this layer's alignment manifest — Returns the agent-scope alignment spec as authored.

Issue the signed completion receipt for a finished Dojo run.

Get a single governance signal by ID

Compute an AI agent's AAP integrity score — a technical reliability metric derived from the agent's own verified checkpoint history.

Return your personal organization, provisioning it if one does not yet exist (idempotent ensure-exists — repeat calls return the same org and never create a second).

List agents in organization

Read a posture's current revision

Get this layer's protection manifest — Returns the agent-scope protection spec as authored.

Look up an AI agent's published Trust Rating — Mnemom's portable reliability signal for autonomous software, computed from the agent's own verified activity record.

Read an AI agent's risk-assessment history — the chronological trail of risk evaluations and correction events on that agent.

Zero-auth, no-args orientation: who Mnemom is, the surface map, how to authenticate and what it unlocks, and the value tools to try right now (headlining scan_trust + the reputation reads).

Get team by ID — Retrieve a team and its current members.

Sideband finding coverage rollup for a team — Per-source counts over a window.

Get webhook delivery log — Paginated delivery log for the organization.

Get webhook endpoint details — Get details for a single webhook endpoint.

Grant team-admin role to a user — Authorized: org_admin / org_owner.

List governance signals affecting a specific agent — Returns governance signals whose `agent_ids` array contains the given agent.

List your agents — List all agents owned by the authenticated user.

List active API keys

List notification destinations for an org

List escalation rules for an org

List organizations for authenticated user

List governance signals for an org — Returns governance signals scoped to the given org, filterable by source, severity, status, and pattern_type.

List teams in organization — List all teams belonging to an organization, filtered by status.

List all revisions of a posture

List postures — Returns platform-default postures plus, when org_id is supplied, the org's postures.

List team-admin grants — Returns users with team-admin role on this team.

List governance signals for a team — Returns governance signals scoped to the given team.

List webhook endpoints — List all webhook endpoints for the organization.

Preview composed alignment (dry run) — Composes the cascade against a hypothetical body at the agent layer and returns conflicts + the composed view.

Preview the composition this posture would produce for a team — Composes alignment + protection cards using the posture body, the team's templates, and per-agent exemptions, without persisting.

Preview composed protection (dry run) — Composes the cascade against a hypothetical body at the agent layer and returns conflicts + the composed view.

Publish or replace the alignment manifest — Accepts YAML (`text/yaml`, `application/yaml`) or JSON.

Write a new revision of a posture (forward-only) — Creates a new immutable revision; updates current_revision_id pointer.

Publish or replace the protection manifest — Accepts YAML (`text/yaml`, `application/yaml`) or JSON.

Query traces with filters

Redeliver a webhook event — Create a new delivery attempt for a previously failed event.

Replay a webhook event to its eligible endpoints — Re-dispatches a previously recorded webhook event to all org endpoints subscribed to its event_type (or to the explicit subset supplied in the request body).

Submit a false-positive / false-negative correction for one of Mnemom's automated detection rules (a 'recipe') — technical feedback that improves detection accuracy, like filing a bug report against a spam filter.

Resolve a governance signal — Closes the signal with a `resolution_status` and optional `action_taken` note.

Revoke an API key

Revoke a team-admin grant — Authorized: org_admin / org_owner.

Rotate a personal API key — Atomically mints a replacement key with the same `name` and `scopes` as the original, then immediately revokes the old key.

Rotate webhook signing secret — Generate a new signing secret for the endpoint.

Scan a website's agent-trust-readiness and return a signed scorecard (Trust, plus an Access axis on newer rubrics).

Resolve an agent name or id-prefix to a real agent_id over the PUBLIC reputation directory (only agents whose reputation visibility is public).

Send a synthetic signal through a destination — Bypasses escalation rules and dispatches a test payload directly to the destination.

Send test webhook delivery — Send a synchronous test delivery to the endpoint with a synthetic webhook.test event.

Unassign a team from a posture — Authorized: org_admin / org_owner / team_admin.

Update webhook endpoint — Update an existing webhook endpoint.

Validate a license key (public)

Verify that an API key is bound to this agent — confirms the holder is the accountable owner (anti-impersonation), hashing the key client-side.

Verify a Dojo completion receipt against the published JWKS.

Attest an agent's Trust Rating — returns a Merkle-root + hash-chain attestation (hash_chain_valid) proving the rating derives from an unbroken, append-only checkpoint chain, plus a pointer to the signed integrity certificate.

Verify a website scan scorecard's Ed25519 signature IN-BAND (verify, don't trust).