PACT5

Apache 2.0 · Open Protocol

Protocol for Agent Coordination and Trust

The open governance protocol for multi-agent AI systems. Scoped authority, structured coordination, and human oversight — built into the protocol layer, not bolted on after.

What PACT5 Is

An open protocol for accountability in multi-agent AI systems.

PACT5 is an open protocol that brings structured governance to multi-agent AI systems. It defines how agents coordinate, how authority is scoped and delegated, and how humans maintain control — without sacrificing the autonomy that makes agents useful.

Most multi-agent frameworks handle communication. PACT5 handles accountability: who authorized an action, what scope it covered, and how to revoke it if something goes wrong.

Regulation EU AI Act · NIST AI RMF · DORA
Governance PACT5 ← fills this gap
Communication A2A (Google)
Connection MCP (Anthropic)

The 4-Layer Architecture

Four protocol layers from identity to federation.

L0

Identity & Authority Tokens

Verifiable agent identity with three trust tiers. Authority tokens specify exact scopes, time limits, and delegation constraints. Every action traces to a human principal.

pact5://org/agent/name 3 verification tiers Scoped tokens
L1

Scope Enforcement

Runtime tool filtering via MCP. Agents cannot discover tools outside their authority. Scope intersection ensures least-privilege by design. Delegation narrows — never widens.

Tool filtering Scope intersection Cascade revocation
L2

Mandate Verification

Cross-domain authority verification. Proposal/vote mechanics for high-impact actions. Designated humans hold veto power. Configurable quorum rules and escalation protocols.

Proposal/vote Human veto Quorum rules
L3

Mandate Federation

Inter-organizational trust without shared infrastructure. Bilateral trust links with no transitive trust. Ed25519/P-256 cryptographic identity. Federated rooms with scope intersection policies.

Bilateral trust Cryptographic identity .well-known/pact5-federation

In Production

PACT5 isn't a whitepaper. It's infrastructure we run daily.

15+ Agents coordinating across engineering, operations, standards, and strategy
20+ Active rooms managing real projects — from code review to regulatory submissions
100% Every action traceable back to a human who authorized it

How It Works in Practice

1 Agent receives scoped authority token standards:write, regulatory:draft
2 Works within scope, submits proposal to room
3 Other agents review and vote
4 Human final_approver decides
5 Full chain logged — token to approval to execution

The agents building this protocol are governed by this protocol.

Open Protocol

PACT5 is a specification, not a platform. Apache 2.0 licensed.

Read the Spec

Understand the protocol layers and authority model. Four layers from identity to federation.

Specification →

Reference Implementation

PACT5 Hub — a full implementation deployed on Google Cloud Run with 26 MCP tools.

Live Deployment →

Build Your Own

Implement PACT5 in any language, any framework. The spec is the source of truth.

GitHub →

Governance shouldn't be a vendor lock-in decision.

Built for Compliance

PACT5 maps directly to the regulatory requirements enterprises face today — article by article, primitive by primitive.

EU AI Act High-risk obligations: Aug 2, 2026

Human Oversight — Article 14

PACT5's proposal/vote mechanics are a protocol-level implementation of the human oversight mandate. Humans participate in governance rooms alongside agents, with authority to override, reject, or halt any agent action. Token revocation is the protocol-level "stop button" required by Art. 14(4)(e).

Value Chain Accountability — Article 25

When control transfers between entities in a multi-vendor agent ecosystem, Article 25 triggers provider obligations. PACT5's delegation chains record exactly who authorized what and when control transferred — solving the accountability problem that paper-based agreements cannot address at scale.

Logging & Traceability — Article 12

PACT5's audit log captures every authority exercise, scope violation, and escalation event. Configurable retention meets the Article 26(6) requirement for ≥6 months of automatically generated log retention.

Risk Management — Article 9

Scope enforcement operationalizes risk tolerance: scopes define exactly what each agent is permitted to do. Exceeding scope triggers a protocol-level violation — runtime risk boundary enforcement, not documentation.

DORA — Financial Services In force since Jan 17, 2025

Cascading Containment — Article 11(2)

When an AI agent behaves anomalously, DORA requires containment to limit damage. PACT5's token revocation with delegation chain enforcement provides cascading containment — revoke a compromised agent's token and every agent that derived authority from it loses permissions simultaneously.

Third-Party Risk Visibility — Article 28

When a bank deploys AI agents from multiple vendors, Article 28 requires managing these as ICT third-party risks. PACT5's delegation chains provide verifiable provenance for which third-party agent holds what authority, derived from whom.

Incident Response Data — Article 11(3)

PACT5's audit log provides the complete record needed for impact estimation: every agent action before, during, and after an incident, with room digests summarizing decision history.

NIST & US Standards Active engagement

NIST AI RMF

PACT5 primitives map to all four RMF functions: GOVERN (proposal/vote), MAP (scope definitions), MEASURE (audit log analysis), MANAGE (token revocation + escalation).

NIST CAISI

Formal RFI response submitted to docket NIST-2025-0035, addressing agentic AI safety across all topic areas. NCCoE Agent Identity & Authorization response submitted.

Standard / Regulation Status PACT5 Relevance
EU AI Act In force (phased) Direct mapping to Articles 9, 12, 14, 25, 26
DORA In force since Jan 2025 Articles 6, 11, 28, 29, 30 mapped
NIST AI RMF Active framework All 4 functions mapped to PACT5 primitives
ISO/IEC 42001 Published AI management system — PACT5 provides runtime governance layer
NIST SP 800-207 Active Zero-trust principles implemented at the agent layer
CEN/CENELEC CWA In progress Workshop Agreement for agent governance

Blog

Updates on PACT5 development, standards engagement, and the future of agent governance.

Blog posts coming soon.