A Manifesto

Ten Factors for
Agent Interoperability

A framework for building AI agents that can discover, communicate with, and trust one another — across platforms, protocols, and organizations.

Read the Full Manifesto Explore the Factors
SCROLL

Ten Principles for the Agentic Internet

Inspired by the 12-Factor App methodology — designed for the age of multi-agent AI systems.

FACTOR 01

Agent Card

Every agent must publish a standard, machine-readable Agent Card — a self-describing document declaring its identity, capabilities, endpoints, and trust metadata.

Identity

FACTOR 02

Open Discoverability

Agent capabilities must be published in a standard, machine-readable format — discoverable by any orchestrator without prior coordination.

Discovery

FACTOR 03

Protocol Neutrality

Agents must not be coupled to a single communication protocol. Support for A2A, MCP, and emerging standards should be composable, not competing.

Protocols

FACTOR 04

Explicit Trust Boundaries

Authorization must be declared, scoped, and verifiable. An agent should never inherit ambient trust — every capability grant must be explicit.

Trust

FACTOR 05

Stateless Interactions

Each agent interaction must carry all the context it needs. Shared mutable state across agent boundaries is a coordination failure waiting to happen.

Architecture

FACTOR 06

Full Observability

Every action an agent takes must emit structured logs, traces, and metrics. Silent agents are unauditable agents — and unauditable agents are ungovernable.

Observability

FACTOR 07

Composable Capabilities

Agents must expose discrete, independently invokable capabilities — not monolithic endpoints. Composability is what enables true multi-agent orchestration.

Composability

FACTOR 08

Human-in-the-Loop Hooks

Every autonomous action chain must expose well-defined escalation points. Humans should be able to intercept, redirect, or halt any agent workflow at any stage.

Governance

FACTOR 09

Graceful Degradation

Agents must fail safely. When a dependency is unavailable or a tool call fails, agents should communicate failure clearly — never silently propagate errors downstream.

Resilience

FACTOR 10

Open by Default

Agent standards must be developed in the open. Interoperability is a collective good — no single vendor, platform, or protocol should own the agentic internet.

Openness

Go Deeper

The Full Manifesto

Read the complete rationale behind each factor — with implementation guidance, protocol references, and the thinking behind the framework.

Read the Manifesto →