Observability with OpenTelemetry

OpenTelemetry exporter for AIP integrity checkpoints and AAP verification results. Send AIP/AAP telemetry to any OTel-compatible observability platform — Langfuse, Arize Phoenix, Datadog, Grafana — with zero custom code.

Why

AIP and AAP produce rich alignment telemetry: integrity verdicts, concerns, verification results, coherence scores, drift alerts. But this data is only useful if it’s observable. This exporter bridges the gap between protocol output and your existing observability stack by mapping everything onto OpenTelemetry spans, events, and metrics.

AIP/AAP Protocol Output ──→ aip-otel-exporter ──→ OTel SDK ──→ Your Platform
                                                      │
                                                      ├── Langfuse
                                                      ├── Arize Phoenix
                                                      ├── Datadog
                                                      ├── Grafana / Tempo
                                                      └── Any OTLP endpoint

Three integration layers

Layer	TypeScript	Python	OTel SDK?	Use Case
Manual API	`@mnemom/aip-otel-exporter`	`aip-otel-exporter[otel]`	Yes	Full control, works everywhere
Auto-instrumentation	`@mnemom/aip-otel-exporter/auto`	`AIPInstrumentor`	Yes	Wraps AIP/AAP calls automatically
CF Workers adapter	`@mnemom/aip-otel-exporter/workers`	—	No	Cloudflare Workers edge runtime

Quick start

TypeScript

npm install @mnemom/aip-otel-exporter @opentelemetry/api

import { createAIPOTelRecorder } from "@mnemom/aip-otel-exporter";

const recorder = createAIPOTelRecorder({ tracerProvider });

recorder.recordIntegrityCheck(signal);    // AIP integrity check → span
recorder.recordVerification(result);       // AAP verification → span
recorder.recordCoherence(result);          // AAP coherence → span
recorder.recordDrift(alerts, count);       // AAP drift detection → span

Python

pip install aip-otel-exporter[otel]

from aip_otel_exporter import AIPOTelRecorder

recorder = AIPOTelRecorder(tracer_provider=provider)

recorder.record_integrity_check(signal)
recorder.record_verification(result)
recorder.record_coherence(result)
recorder.record_drift(alerts, traces_analyzed=50)

Span hierarchy

Spans are created as children of the current active span via context.active():

your_application_span
  ├── aip.integrity_check
  │    ├── event: aip.concern (one per concern)
  │    └── event: aip.drift_alert (when drift active)
  ├── aap.verify_trace
  │    └── event: aap.violation (one per violation)
  ├── aap.check_coherence
  └── aap.detect_drift
       └── event: aap.drift_alert (one per alert)

Attributes reference

For the complete attributes and metrics reference, see OTel Attributes.

`aip.integrity_check` — 31 attributes + 4 GenAI SemConv fields

Attribute	Type	Source
`aip.integrity.checkpoint_id`	string	checkpoint
`aip.integrity.verdict`	string	checkpoint (clear / review_needed / boundary_violation)
`aip.integrity.agent_id`	string	checkpoint
`aip.integrity.card_id`	string	checkpoint
`aip.integrity.session_id`	string	checkpoint
`aip.integrity.thinking_hash`	string	checkpoint (SHA-256)
`aip.integrity.proceed`	boolean	signal
`aip.integrity.recommended_action`	string	signal
`aip.integrity.concerns_count`	int	signal
`aip.integrity.analysis_model`	string	analysis_metadata
`aip.integrity.analysis_duration_ms`	float	analysis_metadata
`aip.integrity.thinking_tokens`	int	analysis_metadata
`aip.integrity.truncated`	boolean	analysis_metadata
`aip.integrity.extraction_confidence`	float	analysis_metadata
`aip.conscience.consultation_depth`	string	conscience_context
`aip.conscience.values_checked_count`	int	conscience_context
`aip.conscience.conflicts_count`	int	conscience_context
`aip.attestation.input_commitment`	string	attestation
`aip.attestation.chain_hash`	string	attestation
`aip.attestation.merkle_root`	string	attestation
`aip.attestation.signature_verified`	boolean	attestation
`aip.attestation.certificate_id`	string	attestation
`aip.attestation.zk_proven`	boolean	attestation
`aip.attestation.zk_proof_time_ms`	float	attestation
`aip.window.size`	int	window_summary
`aip.window.integrity_ratio`	float	window_summary (0.0-1.0)
`aip.window.drift_alert_active`	boolean	window_summary
`aip.integrity.output_hash`	string	output_analysis
`aip.integrity.output_tokens`	int	output_analysis
`aip.integrity.output_truncated`	boolean	output_analysis
`aip.integrity.analysis_scope`	string	output_analysis
`gen_ai.evaluation.verdict`	string	GenAI SIG forward-compat
`gen_ai.evaluation.score`	float	GenAI SIG forward-compat
`gen_ai.system`	string	upstream LLM provider attribution
`gen_ai.request.model`	string	upstream LLM provider attribution

mnemom.span.role (customer / verifier) is also set on some spans so you can filter verifier-internal traffic out of per-provider SLOs. All fields are duck-typed and optional-chained — a missing field is skipped rather than throwing, so partial checkpoints still produce a valid (if sparser) span.

`aap.verify_trace` — 8 attributes

Attribute	Type
`aap.verification.result`	boolean
`aap.verification.similarity_score`	float
`aap.verification.violations_count`	int
`aap.verification.warnings_count`	int
`aap.verification.trace_id`	string
`aap.verification.card_id`	string
`aap.verification.duration_ms`	float
`aap.verification.checks_performed`	string (comma-separated)

`aap.check_coherence` — 5 attributes

Attribute	Type
`aap.coherence.compatible`	boolean
`aap.coherence.score`	float (0.0-1.0)
`aap.coherence.proceed`	boolean
`aap.coherence.matched_count`	int
`aap.coherence.conflict_count`	int

`aap.detect_drift` — 2 attributes

Attribute	Type
`aap.drift.alerts_count`	int
`aap.drift.traces_analyzed`	int

Metrics

9 metric instruments for aggregate monitoring:

Metric	Type	Labels
`aip.integrity_checks.total`	Counter	verdict, agent_id
`aip.concerns.total`	Counter	category, severity
`aip.analysis.duration_ms`	Histogram	verdict
`aip.window.integrity_ratio`	Histogram	—
`aip.drift_alerts.total`	Counter	—
`aap.verifications.total`	Counter	verified
`aap.violations.total`	Counter	type, severity
`aap.verification.duration_ms`	Histogram	—
`aap.coherence.score`	Histogram	compatible

Sideband findings (Trust Posture detectors)

A separate recorder, recorder.recordSidebandFinding(finding), covers fleet-level sideband detector firings (coherence, fault-line, fleet, drift — see Tuning Sideband Detection) rather than per-turn AIP/AAP results. It emits a safe_house.sideband.finding span carrying safe_house.sideband.source, .axis, .team_id, .finding_count, .severity, and .pattern_type, with one span event per affected agent.

Dashboard templates

Pre-built dashboards are available in the aip-otel-exporter repository:

grafana-aip-overview.json — Fleet-wide integrity monitoring
grafana-aip-detail.json — Per-agent deep-dive
datadog-aip-overview.json — Datadog importable dashboard

See the dashboards README for import instructions.

Platform examples

Integration examples are available in the examples directory:

Platform	File
Langfuse	`langfuse.ts`
Arize Phoenix	`arize-phoenix.ts`
Datadog	`datadog.ts`
Cloudflare Workers	`cloudflare-workers.ts`

Performance

Every recorder call (recordIntegrityCheck, recordVerification, recordCoherence, recordDrift) and the Workers-adapter helpers (createOTLPSpan, serializeExportPayload) ship with their own Vitest benchmark (npm run bench in the TypeScript package) — run it against your own hardware and Node version for current numbers. All of them are attribute-mapping and JSON serialization only (no network I/O), so the overhead they add on your hot path is sub-millisecond.

Design principles

Duck-typed inputs — No hard dependency on AIP/AAP packages. Works with any compatible shape.
Graceful degradation — Missing fields are silently skipped, never throws.
Zero-overhead Workers — CF Workers adapter uses only fetch() + crypto, no OTel SDK.
GenAI SIG forward-compat — gen_ai.evaluation.* aliases for future OTel GenAI SIG alignment.

Standards alignment

The exporter follows OpenTelemetry Semantic Conventions for span naming and attribute structure. Forward-compatible aliases (gen_ai.evaluation.*) track the emerging OTel GenAI SIG conventions for AI/ML observability. This exporter is part of the Mnemom trust plane:

AIP — Agent Integrity Protocol (per-turn thinking analysis)
AAP — Agent Alignment Protocol (behavioral verification)
aip-otel-exporter — This package (observability bridge)

Document	Description
CHANGELOG	Release history
CONTRIBUTING	Development setup and contribution guide
Security Policy	Security policy and threat model
TypeScript README	TypeScript package documentation
Python README	Python package documentation
Dashboards README	Dashboard import instructions

Versions

Package	Version
`@mnemom/aip-otel-exporter` (npm)	0.13.0
`aip-otel-exporter` (PyPI)	0.5.0

Identity & Cards

Posture & Policy

Detection & Safe House

Reputation & Risk

Lifecycle

Observability with OpenTelemetry

Why

Three integration layers

Quick start

TypeScript

Python

Span hierarchy

Attributes reference

`aip.integrity_check` — 31 attributes + 4 GenAI SemConv fields

`aap.verify_trace` — 8 attributes

`aap.check_coherence` — 5 attributes

`aap.detect_drift` — 2 attributes

Metrics

Sideband findings (Trust Posture detectors)

Dashboard templates

Platform examples

Performance

Design principles

Standards alignment

See also

Versions

​Why

​Three integration layers

​Quick start

​TypeScript

​Python

​Span hierarchy

​Attributes reference

​aip.integrity_check — 31 attributes + 4 GenAI SemConv fields

​aap.verify_trace — 8 attributes

​aap.check_coherence — 5 attributes

​aap.detect_drift — 2 attributes

​Metrics

​Sideband findings (Trust Posture detectors)

​Dashboard templates

​Platform examples

​Performance

​Design principles

​Standards alignment

​See also

​Versions

Why

Three integration layers

Quick start

TypeScript

Python

Span hierarchy

Attributes reference

`aip.integrity_check` — 31 attributes + 4 GenAI SemConv fields

`aap.verify_trace` — 8 attributes

`aap.check_coherence` — 5 attributes

`aap.detect_drift` — 2 attributes

Metrics

Sideband findings (Trust Posture detectors)

Dashboard templates

Platform examples

Performance

Design principles

Standards alignment

See also

Versions