agent-passport-system

Enforcement and accountability layer for AI agents. Bring your own identity (did:key, did:web, SPIFFE, OAuth, did:aps). Gateway enforcement boundary, monotonic narrowing, cascade revocation, spending controls, data lifecycle, observation governance (telemetry scopes, derivation rights, behavioral memory). Use when agents need scoped delegation, trust scoring, constraint enforcement, or cryptographic audit trails. SDK leads with the /core subpath (24 curated functions), MCP leads with APS_PROFILE=essential (20 tools covering identity, delegation, enforcement, commerce, reputation). 4,098 tests. 8 framework adapters: Stripe, Composio, IBAC/Cedar, LangChain, CrewAI, MCP, A2A, Gonka. Full surface area (107 modules, 150 MCP tools) still available under APS_PROFILE=full and the root import. SDK 3.3.1 on npm adds the Delegated Action Evidence release: bilateral pair reconciliation with five mismatch classes, verifier-side revocation observation receipts under a stated freshness contract, Merkle-rooted evidence bundl

The one skill an AI agent adds to itself to become verifiable, accountable, and interoperable. It gives the agent an Ed25519 identity it controls, provable operation within the authority delegated to it, its own cryptographic receipt chain it can cite, the ability to communicate, delegate, and transact with other agents that speak the Agent Passport System protocol, and a durable way to carry intent and accountable state across sessions and handoffs. One slug, modular, continuously updated on the same cadence as the SDK and MCP. Use when an agent needs to be verifiable, work with other agents, and operate accountably across long or multi-session work. It makes the agent more trusted and more able to work with others. It does not grant autonomy from the principal; the agent still acts only within the authority delegated to it.

The base layer an AI agent runs on to be verifiable, accountable, and able to work with the world. One slug adds a controlled Ed25519 identity tied to the principal behind the agent, scoped authority that only narrows, a signed receipt for every action the agent can carry across sessions and handoffs, and a connection layer so the agent can find the people, companies, and other agents needed to get a task done, every connection principal-approved and double opt-in. Modular, updated on the same cadence as the SDK and MCP. The agent acts only within delegated authority and never connects, publishes, or shares identity without explicit approval.

Early release. The AEOESS skill for agents that operate accountably: verifiable Ed25519 identity tied to the principal, scoped authority that only narrows, and a signed receipt for every action, built on the Agent Passport System. The agent acts only within delegated authority. Apache-2.0. This is an early release; capability is expanding.