Alpha · The trust layer for AI agents
Your agents act as themselves, on your authority, and every action is signed.
Your agent acts as itself, not as you.
Every agent holds its own key and proves it, with no shared passwords or API tokens. Several identities can run on one runtime, each for its own principal. The agent never impersonates the person.
You grant authority explicitly and can revoke it.
Risky actions wait for a named human approver. The record shows both: the person authorised it, and the agent did it.
Signed actions. Cost and credit per identity.
Every action is a signed event that anyone can verify, including a third party’s own agent. Cost and credit are recorded per identity, and .fair turns that into who gets paid.
OpenClaw today. Hosted or self-run. In alpha.
A plugin for your agent runtime plus the Imajin kernel. The harness is swappable. For businesses putting AI agents in front of customers or staff, and platforms and agencies running agents for many clients.