Open-Source Protocol · v0.5

Human authorization
for consequential AI actions.

AI agents carry no authority of their own. Before an agent moves money, changes records, sends communication, grants access, or touches infrastructure, the action must receive a signed pre-execution receipt linked to human authorization.

Read the Protocol

The core invariant

No receipt. No execution.

The receipt is not a post-execution log. It is the precondition for execution — and the audit artifact proving the action was authorized before it ran.

Execution receipt signed · pre-execution
decision_owner
did:eudi:at:9f21… — authorizing human, via attestation
profile
charge@0.5
bounds_hash
sha256:7a91…
action_type
refund
execution
order #4821 · €48.00
cumulative
€391 / €500 today — AS-tracked
issued
2026-05-23T14:22Z
signature
ed25519:8f3b…1b4c
  1. A human authorizes bounded execution — scope, limits, time, and commitment mode.
  2. The Gatekeeper verifies the attestation, checks per-action bounds, and enforces local context constraints.
  3. The Authority Server checks cumulative limits, expiry, and revocation, then signs the receipt.
  4. The Executor runs the action — only after the receipt exists.

Open infrastructure. Any compliant Authority Server can issue receipts — Suveren is one implementation. The protocol is open; no single vendor owns the trust layer.

Where it fits

HAP composes. It doesn't compete.

HAP isn't another login, API gateway, or agent framework. It's the layer that decides whether an already-reachable capability may be used for a consequential action — with proof.

LayerWhat it does
OAuth / OpenID ConnectGrants API access
MCPExposes tools to agents
Identity (EUDI, passkeys, WebAuthn)Proves who you are
HAPAuthorizes the consequential action — before it runs, with a signed receipt

OAuth grants reachable capability. HAP governs authorized use of that capability.

Commitment modes

You decide how much runs on its own.

The level of autonomy is a signed choice on every authorization — the protocol's commitment mode, not a default the agent can change.

AutomaticAgent runs within bounds

The agent acts within the bounds you set. No per-action approval — the Authority Server enforces the limits and issues a signed receipt for each action before execution.

ReviewYou approve each action

The agent proposes; you approve each action before it runs. No approval, no receipt — no execution.

Review above a capApprovers sign above a limit

The agent runs on its own under a limit you set. Above it, the action routes to a named set of approvers before any receipt is issued.

The distinction

Agents aren't employees. They're executors.

Most systems give agents their own accounts, credentials, and standing permissions — one more identity to manage. HAP does the opposite.

An agent never carries authority of its own. A human authorizes a bounded action; the receipt is cryptographic proof that this specific action was authorized — and issued before it ran. An agent may have technical identifiers for logging and routing, but it holds no independent authority.

As AI systems become more capable, HAP keeps authority from quietly moving from humans into machines.

The model choice

Two models for authorizing agents.

How a system treats agent authority is an architectural decision with long-term governance consequences.

Agent-identity approach HAP approach
Treat agents as authority-bearing actors Treat agents as executors
Manage standing agent permissions Issue bounded action receipts
Rely on accounts and credentials Bind execution to human authorization
Audit after execution Verify the receipt before execution
Agent acts under standing authority Agent acts only inside receipt-approved bounds

EU AI Act — Article 14

Article 14 requires effective human oversight of high-risk AI. HAP turns that oversight into an enforceable control at the action layer: consequential actions cannot run unless a human-linked authorization receipt exists before execution.

HAP is Article-14-enabling infrastructure — not compliance on its own. Compliance still requires governance, training, documentation, and human competence.

Use cases

Where consequential actions need proof.

Paymentsrefunds, charges, payouts
Emailhigh-stakes sends
CRMrecord changes & deletes
Infrastructuredeploys & config
Multi-owner approvalstwo people must sign
Compliance auditverifiable receipts

Open infrastructure

No single vendor owns the trust layer.

HAP is an open standard — MIT-licensed, developed in the open, and maintained by stewards, not owners. Any compliant Authority Server can issue receipts.