Skip to main content
The trust plane for the agentic internet. Mnemom makes AI agent behavior transparent and verifiable. When an agent makes a decision, Mnemom records what it decided, what alternatives it considered, what values it applied, and whether its reasoning was compromised. The result is a verifiable audit trail that any stakeholder can inspect. Three layers power this:
  • AAP (Agent Alignment Protocol) — Post-hoc verification. Alignment Cards declare an agent’s values and boundaries. AP-Traces record every decision. Verification checks whether behavior is consistent with declared intent.
  • AIP (Agent Integrity Protocol) — Per-turn integrity checking. Analyzes LLM thinking blocks during execution to detect prompt injection, value drift, and manipulation; in enforce it gates the response before the agent acts, while observe and nudge record the verdict post-hoc. AIP reads reasoning, not inbound content: the content itself is screened by Safe House at the gateway’s front door, inside the request that carries it — including tool results returning from a tool call.
  • CLPI (Card Lifecycle & Policy Intelligence) — Governance-as-code that enforces what tools agents may use, distinguishes configuration errors from behavioral failures, recovers trust after false violations, and anchors reputation on-chain.
What Mnemom guarantees: Complete audit trails of every agent decision (AAP), per-turn attestation of reasoning integrity at the thinking level (AIP), and active policy enforcement that blocks prohibited actions at the gateway in enforce mode (CLPI). Together, these provide verifiable accountability from declared intent through execution.What no external system can guarantee: Enforcement at the sub-thinking level — inside the model’s weights. If a model produces compromised reasoning that does not surface in its thinking blocks, no external observer can detect it. Mnemom verifies everything the model externalizes; it cannot inspect what the model does not reveal. See the limitations docs for details.

​
Start here

Five steps from zero to a governed agent. Every command below is taken from the gateway quickstart, the CLI reference and MCP clients — follow those pages for options and troubleshooting.
1

Install the CLI and log in

mnemom login opens a browser. On a machine with no browser (SSH, a container), run mnemom login --no-browser instead.
2

Connect the MCP server (optional)

Let your coding agent read and manage your Mnemom agents directly. The control-plane server needs a Bearer access token or mnm_… API key; the docs server needs no auth.
Other clients (Cursor, VS Code and more) are covered in MCP clients.
3

Send traffic through the gateway, then claim your agent

Point your LLM call at the gateway and name your agent with the x-mnemom-agent header. Use -i to print response headers and note the X-Mnemom-Agent id.
Claim the agent so it belongs to your account:
See Gateway quickstart for other providers and the full claim flow.
4

See your traffic

From the terminal:
Or open the dashboard and select your agent: the conscience timeline lists every trace, integrity checkpoint and enforcement action, alongside integrity scores, drift alerts and the enforcement log. Through MCP, ask your coding agent to run query_traces for the agent.
5

Configure your cards

The Alignment Card declares your agent’s values and boundaries; the Protection Card sets its Safe House screening. Change either one from whichever surface you prefer:
  • Dashboard — open your agent in the dashboard and edit its Alignment Card.
  • CLI — mnemom card show|edit --agent my-agent and mnemom protection show|edit --agent my-agent. See CLI reference.
  • MCP — get_alignment_by_agent, put_alignment_by_agent, get_protection_by_agent and put_protection_by_agent.

​
Other ways to integrate

These quickstarts are available in Spanish (Español) and French (Français) — six pages per language have been translated.

Mnemom Gateway

Recommended. Wrap any LLM API with zero code changes. Full AAP and AIP compliance in minutes.

SDK Direct

Integrate AAP and AIP directly into your application for maximum control over tracing and verification.

Self-Hosted

Run the Mnemom gateway on your own infrastructure. Full data residency control.

Safe House Protection

Bolt on inbound/outbound threat screening for an agent you’ve already registered.
See the quickstart overview for a full comparison of all four paths. Building with a coding agent instead? Mnemom Agent launches your coding-agent CLI (Claude Code today) through the gateway under a governed identity in one command.

​
Key concepts

Alignment Cards

A machine-readable declaration of an agent’s values, autonomy boundaries, escalation triggers, and audit commitments. The “constitution” every trace is verified against.

AP-Traces

Structured records of agent decisions — what action was taken, what alternatives were considered, what values were applied, and whether escalation was required.

Integrity Checkpoints

Per-turn AIP analysis of LLM thinking blocks. Each checkpoint produces a verdict: clear, review_needed, or boundary_violation.

Drift Detection

Statistical monitoring of agent behavior over time. Detects when an agent’s actions gradually diverge from its declared alignment.

CLPI: Governance Layer

Card Lifecycle & Policy Intelligence. Governance-as-code with policy enforcement, violation reclassification, trust recovery, risk intelligence, and on-chain reputation anchoring.

Mnemom Trust Rating

A credit score for AI agents. Five-component composite metric computed from integrity checkpoints, drift stability, compliance, trace completeness, and fleet coherence. Cryptographically provable and anchorable on-chain.

Team Reputation

Teams are first-class meta-agents with persistent identity, their own alignment cards, and accumulated reputation — independent of any individual member.

Verifiable Integrity

Four-layer cryptographic attestation: Ed25519 signatures, hash chains, Merkle proofs, and optional SP1 zero-knowledge proofs. Any party can independently verify a verdict without trusting Mnemom.

Agent Containment

Kill-switch for rogue agents. Pause, kill, and resume agents in real-time with auto-containment triggers, RBAC controls, and full audit trails.

Value Coherence

Pairwise compatibility checking between agents. Before two agents collaborate, coherence checks verify their values are not in conflict.

​
SDK packages

Install the protocol SDKs directly if you need fine-grained control:
Canonical Python package names: PyPI: agent-integrity-proto (AIP) and agent-alignment-protocol (AAP); npm: @mnemom/agent-integrity-protocol (AIP) and @mnemom/agent-alignment-protocol (AAP). These are the only published package names — do not install packages under any other name.

​
Protocols

Protocol Overview

How AAP and AIP work together as complementary verification layers.

AAP Specification

Full Agent Alignment Protocol specification for implementers.

AIP Specification

Full Agent Integrity Protocol specification for implementers.

Security Model

Threat models, attack surfaces, and known limitations.