Skip to content
Metamynd
Platform Engine

Agent Passport

A signed, portable snapshot of an agent's identity, ownership, declared purpose and current capabilities — composed from data the platform already tracks.

Overview

What it does

An Agent Passport is a signed, point-in-time snapshot of everything that answers 'what is this agent, right now': its verified identity and owner, declared purpose, model provider, the hashes of its current system prompt / tool manifest / config, its declared capabilities and active roles, and its assurance status. It isn't a new source of truth — every field is composed from data the Identity Engine and Ownership & Delegation already maintain — it's the portable, signed document you hand a counterparty instead of asking them to trust your dashboard. Renewing it (a new agent version, an assurance change) issues a new passport rather than mutating the old one, so history is preserved, and a passport can be revoked independently of the agent itself — an owner can stop presenting a credential without quarantining the agent it describes.

Core Functions

Inside Agent Passport

The core functions this engine provides across the Trust Fabric.

Signed identity + capability snapshot
Composed from existing identity/version/assurance data
Independently revocable from containment
Reissued as the agent's profile changes
One platform

Agent Passport composes with the Trust Fabric

Every engine is independently useful and interoperates through one API-first Trust Fabric — so identity, evidence, policy, risk and certification stay consistent across your AI estate.

Explore more

Related engines

Credential Authority

Issues, presents and verifies W3C Verifiable Credentials — with selective disclosure and on-chain anchoring.

  • Verifiable Credentials (identity, entity, mandate)
  • BBS selective disclosure
  • Ed25519 platform issuer
  • Anchoring & revocation
View engine

Policy Engine

The deterministic core: composes Standards & SOPs from atoms and returns allow / observe / block / escalate — no LLM in the decision.

  • Atom → molecule → SOP/Standard
  • allow / observe / block / escalate
  • Deterministic & re-derivable
  • Live edits, no redeploy
View engine

Governance Engine

The authorize gate that runs the policy on every signed action, in cooperative or trustless mode, with human-in-the-loop escalation.

  • The authorize gate (MAGP)
  • Escalation → owner approval
  • Standards compliance check
  • Cooperative & trustless modes
View engine

See Agent Passport in action

Book a demo and see how the platform establishes trust across your AI systems.