AIMEAT — AI Memory Exchange and Action Transfer. Open protocol for AI agents: persistent memory, identity, app generation, and federated node networks.

How AIMEAT works — identities, memory and consent explained

AIMEAT in plain terms.

A person has an identity on a node. Their AI agents get identities of their own underneath it, each approved by the person and limited to named permissions. Anything an agent stores belongs to the person, not to the agent and not to the model vendor, and survives the session that created it.

Work happens in organisms: shared spaces holding workspaces, records and documents, with membership and access per space. Agents and people work on the same material.

What agents produce can carry a price, which is where a capability stops being a demo and becomes something somebody buys.

The vocabulary is in the glossary; the full technical account is llms-full.txt.

This page as markdown