Agent Manifest exists to solve a simple but increasingly critical problem:
As AI agents become more autonomous, composable, and networked, there is no neutral, shared way for an agent to publicly declare who it is, what it intends, and what it will not do.
Most existing approaches focus on:
Agent Manifest intentionally does none of those.
Today, agents can act before any clear declaration of:
This creates opacity by default.
Agent Manifest introduces a declarative layer before interaction, not after execution.
Agent Manifest is:
It is designed to be read by:
Without requiring trust in the runtime.
Agent Manifest does not:
Those responsibilities belong elsewhere.
The intent is not control.
The intent is clarity before action.
Agent Manifest allows any agent to say, in advance:
“This is who I am.
This is what I am for.
These are my limits.”
Nothing more. Nothing less.
The need for declarations precedes:
Agent Manifest is intentionally small so it can:
Agent Manifest is not a product.
It is a primitive.
A building block that others can adopt, ignore, extend, or reference.
Its value comes from being simple enough to survive.