Mnemom Checkpoints API
Integrity checkpoints and proof artifacts.
Integrity checkpoints and proof artifacts.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/mnemom-ai:mnemom-ai-checkpoints-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Mnemom Checkpoints API
description: Trust infrastructure for AI agents. Transparent alignment verification, behavioral drift detection, and accountability primitives.
version: 1.0.0
contact:
name: Mnemom
url: https://mnemom.ai
email: support@mnemom.ai
license:
name: Apache 2.0
url: https://www.apache.org/licenses/LICENSE-2.0
servers:
- url: https://api.mnemom.ai/v1
description: Production
security:
- BearerAuth: []
- ApiKeyAuth: []
tags:
- name: Checkpoints
description: Integrity checkpoints and proof artifacts.
paths:
/agents/{agent_id}/checkpoints:
get:
operationId: listCheckpoints
security:
- BearerAuth: []
- ApiKeyAuth: []
- CookieAuth: []
summary: Paginated integrity checkpoints
tags:
- Checkpoints
parameters:
- $ref: '#/components/parameters/AgentId'
- name: limit
in: query
schema:
type: integer
default: 20
minimum: 1
maximum: 1000
- name: offset
in: query
schema:
type: integer
default: 0
minimum: 0
- name: verdict
in: query
schema:
type: string
enum:
- clear
- review_needed
- boundary_violation
- unverified
- unanalyzed
- name: session_id
in: query
schema:
type: string
responses:
'200':
description: Paginated checkpoints
content:
application/json:
schema:
type: object
properties:
checkpoints:
type: array
items:
$ref: '#/components/schemas/Checkpoint'
total:
type: integer
limit:
type: integer
offset:
type: integer
'400':
$ref: '#/components/responses/BadRequest'
'401':
$ref: '#/components/responses/Unauthorized'
'403':
$ref: '#/components/responses/Forbidden'
'404':
$ref: '#/components/responses/NotFound'
'429':
$ref: '#/components/responses/TooManyRequests'
'500':
$ref: '#/components/responses/InternalServerError'
/agents/{agent_id}/checkpoints/{checkpoint_id}:
get:
operationId: getCheckpoint
security:
- ApiKeyAuth: []
- BearerAuth: []
- CookieAuth: []
summary: Get single checkpoint
description: 'Authorization: authentication is required (401 without credentials), and the caller must be an `owner`, `admin` or `member` of the organization that owns `agent_id` — checkpoint telemetry is member-only; there is no anonymous read. `checkpoint_id` is queried together with `agent_id`. A checkpoint under an agent the caller cannot access (the caller is not in the agent''s organization, or the agent does not exist) returns the same 404 as a checkpoint that does not exist, as does one belonging to a different agent — never another tenant''s data. A `viewer` or `auditor` of the agent''s own organization gets 403: they can already see the agent exists.'
tags:
- Checkpoints
parameters:
- $ref: '#/components/parameters/AgentId'
- name: checkpoint_id
in: path
required: true
schema:
type: string
responses:
'200':
description: Checkpoint details
content:
application/json:
schema:
$ref: '#/components/schemas/Checkpoint'
'400':
$ref: '#/components/responses/BadRequest'
'401':
$ref: '#/components/responses/Unauthorized'
'403':
$ref: '#/components/responses/Forbidden'
'404':
$ref: '#/components/responses/NotFound'
'429':
$ref: '#/components/responses/TooManyRequests'
'500':
$ref: '#/components/responses/InternalServerError'
/agents/{agent_id}/failover-events:
get:
operationId: listFailoverEvents
security:
- BearerAuth: []
- ApiKeyAuth: []
- CookieAuth: []
summary: Paginated model-failover events
description: 'Reads `model_failover_events`: rows recorded at checkpoint-write time whenever the (provider, model) reported on a checkpoint differs from the immediately preceding checkpoint in the same session. Each row is strictly an OBSERVED provider/model change — this API has no visibility into *why* the change happened, so `reason` is always null today. Same owner-scoped read gate as GET /v1/agents/{agent_id}/checkpoints (no new authorization surface).'
tags:
- Checkpoints
parameters:
- $ref: '#/components/parameters/AgentId'
- name: limit
in: query
schema:
type: integer
default: 20
minimum: 1
maximum: 1000
- name: offset
in: query
schema:
type: integer
default: 0
minimum: 0
- name: from
in: query
description: ISO-8601 lower bound (inclusive) on detected_at.
schema:
type: string
format: date-time
- name: to
in: query
description: ISO-8601 upper bound (inclusive) on detected_at.
schema:
type: string
format: date-time
responses:
'200':
description: Paginated model-failover events
content:
application/json:
schema:
type: object
properties:
failover_events:
type: array
items:
type: object
properties:
event_id:
type: string
agent_id:
type: string
session_id:
type: string
from_provider:
type: string
from_model:
type: string
to_provider:
type: string
to_model:
type: string
triggering_checkpoint_id:
type:
- string
- 'null'
reason:
type:
- string
- 'null'
detected_at:
type: string
format: date-time
created_at:
type: string
format: date-time
limit:
type: integer
offset:
type: integer
'400':
$ref: '#/components/responses/BadRequest'
'401':
$ref: '#/components/responses/Unauthorized'
'403':
$ref: '#/components/responses/Forbidden'
'404':
$ref: '#/components/responses/NotFound'
'429':
$ref: '#/components/responses/TooManyRequests'
'500':
$ref: '#/components/responses/InternalServerError'
/agents/{agent_id}/reverify:
post:
operationId: reverifyTraces
summary: Re-verify AAP traces against updated card
description: Re-runs AAP structural verification of the agent's stored traces against its currently-active alignment card. **Paginated, and a single call is not a full re-verification:** at most 40 traces are processed per call (Cloudflare Workers subrequest limit). Use `has_more` / `next_offset` to walk the remainder — a caller that stops after one page leaves later traces carrying verdicts from the previous card. `complete` is true only when the pass reached the end of the agent's traces with no write errors; the reputation score is recomputed only on such a pass, and `reputation_recompute_skipped_reason` says why it was not.
tags:
- Checkpoints
parameters:
- $ref: '#/components/parameters/AgentId'
- name: limit
in: query
schema:
type: integer
default: 40
maximum: 40
- name: offset
in: query
schema:
type: integer
default: 0
responses:
'200':
description: Re-verification results
content:
application/json:
schema:
type: object
properties:
agent_id:
type: string
card_id:
type: string
total_traces_in_batch:
type: integer
offset:
type: integer
limit:
type: integer
reverified:
type: integer
still_violating:
type: integer
now_clean:
type: integer
total_traces:
type:
- integer
- 'null'
description: Exact total number of traces stored for this agent, or null if the count could not be established. Null means coverage is UNKNOWN — not zero, and not complete.
traces_scanned:
type: integer
description: offset + rows processed in this call.
has_more:
type: boolean
description: True if traces beyond this page remain un-re-verified.
next_offset:
type:
- integer
- 'null'
description: Offset to pass to the next call, or null when there is no next page.
complete:
type: boolean
description: True only if this pass reached the end of the agent's traces with no write errors. False means the agent's history is NOT yet fully consistent with the current card.
reputation_recomputed:
type: boolean
description: Whether the agent's reputation score was recomputed. Only ever true on a complete pass that updated at least one trace.
reputation_recompute_skipped_reason:
type:
- string
- 'null'
enum:
- incomplete_pass
- trace_total_unknown
- write_errors_in_batch
- no_traces_updated
- recompute_failed
- null
errors:
type:
- array
- 'null'
items:
type: string
'400':
$ref: '#/components/responses/BadRequest'
'401':
$ref: '#/components/responses/Unauthorized'
'403':
$ref: '#/components/responses/Forbidden'
'404':
$ref: '#/components/responses/NotFound'
'429':
$ref: '#/components/responses/TooManyRequests'
'500':
$ref: '#/components/responses/InternalServerError'
'502':
$ref: '#/components/responses/BadGateway'
/agents/{agent_id}/reverify/aip:
post:
operationId: reverifyAipCheckpoints
summary: Re-evaluate AIP checkpoints against updated card
tags:
- Checkpoints
parameters:
- $ref: '#/components/parameters/AgentId'
- name: limit
in: query
schema:
type: integer
default: 20
maximum: 20
- name: offset
in: query
schema:
type: integer
default: 0
responses:
'200':
description: Re-evaluation results
content:
application/json:
schema:
type: object
properties:
agent_id:
type: string
card_id:
type: string
total_in_batch:
type: integer
offset:
type: integer
limit:
type: integer
re_evaluated:
type: integer
resolved_to_clear:
type: integer
kept_non_clear:
type: integer
results:
type: array
items:
type: object
errors:
type:
- array
- 'null'
items:
type: string
'400':
$ref: '#/components/responses/BadRequest'
'401':
$ref: '#/components/responses/Unauthorized'
'403':
$ref: '#/components/responses/Forbidden'
'404':
$ref: '#/components/responses/NotFound'
'409':
$ref: '#/components/responses/Conflict'
'429':
$ref: '#/components/responses/TooManyRequests'
'500':
$ref: '#/components/responses/InternalServerError'
/agents/{agent_id}/timeline:
get:
operationId: getTimeline
security:
- BearerAuth: []
- ApiKeyAuth: []
- CookieAuth: []
summary: Unified dual-rail AIP + AAP timeline
tags:
- Checkpoints
parameters:
- $ref: '#/components/parameters/AgentId'
- name: limit
in: query
schema:
type: integer
default: 50
maximum: 200
responses:
'200':
description: Timeline events
content:
application/json:
schema:
type: object
properties:
agent_id:
type: string
events:
type: array
items:
type: object
total:
type: integer
summary:
type: object
'400':
$ref: '#/components/responses/BadRequest'
'401':
$ref: '#/components/responses/Unauthorized'
'403':
$ref: '#/components/responses/Forbidden'
'404':
$ref: '#/components/responses/NotFound'
'429':
$ref: '#/components/responses/TooManyRequests'
'500':
$ref: '#/components/responses/InternalServerError'
'502':
$ref: '#/components/responses/BadGateway'
components:
responses:
Conflict:
description: Resource conflict — the request cannot proceed because of a current state conflict (e.g., resource already exists, version mismatch, in-flight idempotency key with a different body).
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
Unauthorized:
description: Authentication required
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
BadGateway:
description: An upstream dependency returned an invalid response.
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
TooManyRequests:
description: Rate-limit exceeded. The global per-IP limiter (100 requests/minute, applied to every `/v1/*` route) rejected this request. Back off until the window resets — `Retry-After` carries the cooldown in seconds and `X-RateLimit-Reset` the absolute reset time.
headers:
Retry-After:
description: Seconds to wait before retrying.
schema:
type: integer
minimum: 1
X-RateLimit-Limit:
description: Requests permitted per window.
schema:
type: integer
X-RateLimit-Remaining:
description: Requests remaining in the current window (0 on a 429).
schema:
type: integer
minimum: 0
X-RateLimit-Reset:
description: Unix epoch seconds at which the current window resets.
schema:
type: integer
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
InternalServerError:
description: Server error — request was well-formed but the server failed to fulfill it. Typically a downstream dependency (DB / RPC / external API) returned an unexpected error.
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
Forbidden:
description: Forbidden
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
BadRequest:
description: Bad request
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
NotFound:
description: Resource not found
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
schemas:
Checkpoint:
type: object
properties:
checkpoint_id:
type: string
request_id:
type: string
nullable: true
description: The gateway's per-proxied-request id (ADR-065 mnemom_request_id), when the gateway wrote this checkpoint with a request-scoped logger. Null on rows written before migration 548 or by a caller with no request context.
agent_id:
type: string
card_id:
type: string
session_id:
type: string
timestamp:
type: string
format: date-time
thinking_block_hash:
type: string
provider:
type: string
model:
type: string
verdict:
type: string
enum:
- clear
- review_needed
- boundary_violation
- unverified
- unanalyzed
description: '`unverified`: analysis was supposed to run but did not complete. `unanalyzed`: the agent''s integrity_mode is off (AIP off), so the turn was recorded but never analysed (migration 518). Neither is a clean integrity pass.'
concerns:
type: array
items:
type: object
properties:
category:
type: string
severity:
type: string
description:
type: string
evidence:
type: string
reasoning_summary:
type: string
conscience_context:
type: object
window_position:
type: object
properties:
index:
type: integer
window_size:
type: integer
analysis_metadata:
type: object
linked_trace_id:
type:
- string
- 'null'
re_evaluated_at:
type:
- string
- 'null'
format: date-time
original_verdict:
type:
- string
- 'null'
Error:
type: object
description: Canonical error envelope (ADR-API-001 conv 1). `error` is always an object — never a bare string. Every 4xx/5xx response across the API conforms to this shape; the runtime helper is `src/http-errors.ts::buildErrorBody`.
required:
- error
properties:
error:
type: object
required:
- code
- message
properties:
code:
type: string
pattern: ^[a-z][a-z0-9_]*$
description: 'Stable, machine-matchable failure identifier (lowercase snake_case). Clients may branch on this; the string is part of the contract.
**Status-class defaults** — emitted when no caller code is supplied (`errorCodeForStatus(status)`): `bad_request` (400), `unauthorized` (401), `forbidden` (403), `not_found` (404), `method_not_allowed` (405), `conflict` (409), `gone` (410), `precondition_failed` (412), `payload_too_large` (413), `unsupported_media_type` (415), `unprocessable_entity` (422), `precondition_required` (428), `rate_limited` (429), `internal_error` (500), `not_implemented` (501), `bad_gateway` (502), `service_unavailable` (503), `gateway_timeout` (504). Fallback `error` for unmapped statuses.
**Caller-supplied codes** — handlers may pass an explicit `code` for a specific failure class. Examples: `agent_not_found`, `invalid_hash_proof`, `already_linked`, `idempotency_conflict`, `feature_gated`, `schema_validation_failed`, `no_token`, `bad_canonical_payload`.
**Care-framed sub-resource codes** — the cards-as-primitive surface passes its stable care code-string straight through as `error.code`. Examples: `if_match_absent`, `if_match_stale`, `if_match_malformed`, `primitive_validation_failed`.'
message:
type: string
description: Human-readable, care-framed explanation of the failure.
details:
description: 'Optional structured context for the failure (any JSON value: object, array, or primitive). Common shapes: validation findings list, idempotency-conflict diff, `{presented_etag, current_etag}` on a stale `If-Match`, etc. Mirrors the helper''s `details?: unknown`.'
parameters:
AgentId:
name: agent_id
in: path
required: true
schema:
type: string
description: Agent identifier (e.g. smolt-abc123)
securitySchemes:
BearerAuth:
type: http
scheme: bearer
bearerFormat: JWT
description: 'Supabase JWT token in Authorization: Bearer header'
ApiKeyAuth:
type: apiKey
in: header
name: X-Mnemom-Api-Key
description: Mnemom API key (mnm_... format)
ServiceRole:
type: http
scheme: bearer
bearerFormat: JWT
description: Supabase service role bearer JWT. Used by /blog admin operations that talk directly to Supabase. NOT used by /internal/* or /v1/arena/internal/* — those use the custom-header schemes below.
InternalKeyAuth:
type: apiKey
in: header
name: X-Internal-Key
description: Internal service-to-service shared secret, timing-safe compared against INTERNAL_API_KEY. Used by /internal/* gateway routes (compose, agents, webhooks emit).
ServiceKeyAuth:
type: apiKey
in: header
name: X-Service-Key
description: Service-to-service shared secret, timing-safe compared against MNEMOM_SERVICE_KEY. Used by /v1/arena/internal/*, /v1/on-chain/*, and the /v1/internal/* readers consumed by the reputation cron.
CoherenceTokenAuth:
type: http
scheme: bearer
description: Per-cell coherence bearer token. Provisioned in 1Password vault `mnemom-coherence` (one item per receiver). Value compared against COHERENCE_<NAME>_SERVICE_TOKEN_EXPECTED. Used by /v1/internal/coherence/* and /v1/internal/governance/dispatch.
ArenaCandidateTokenAuth:
type: http
scheme: bearer
description: Dedicated arena writer token (ADR-004 §"Arena dedicated writer token"). Compared against ARENA_RECIPE_CANDIDATE_TOKEN. The token's only capability is writing recipe candidates with writer_identity='arena-bypass' (stamped server-side). Used by POST /v1/internal/recipe-candidates.
CustomerVoiceTokenAuth:
type: http
scheme: bearer
description: Customer Voice API bearer token. Timing-safe compared against CUSTOMER_VOICE_API_TOKEN. Grants access to all /v1/internal/feedback/* endpoints (MNE-1876). No customer-facing or reporter-read capability.
CookieAuth:
type: apiKey
in: cookie
name: mnemom_session
description: 'HttpOnly, Secure, SameSite=Lax cookie issued by /v1/auth/sign-in (or the SSO / email-callback flows). The value is an AES-256-GCM-encrypted blob of {access_token, refresh_token, issued_at, auth_method}. Browser clients include this automatically with `credentials: "include"`.'
LicenseJwtAuth:
type: http
scheme: bearer
bearerFormat: JWT
description: License JWT (HS256, HMAC-signed with LICENSE_SIGNING_SECRET). Used by self-hosted deployment instances to authenticate `/v1/deployments/heartbeat`. Not interchangeable with the Supabase user JWT.
AgentAuth:
type: apiKey
in: header
name: X-Mnemom-Agent-Proof
description: 'Agent possession proof: the full SHA-256 hex digest of `${apiKey}|${agentName}` (or `${apiKey}` for an unnamed singleton agent) — the same `hash_proof` primitive used by POST /v1/agents claim, link-agent, and verify-binding. The server resolves the agent by `agent_hash = proof[:16]`. The agent''s *own* identity (ADR-API-001 third auth class) — distinct from ApiKeyAuth (`X-Mnemom-Api-Key`, which resolves a user/account, not an agent).'