KYA Mission Control
A trust layer for AI agents on missions: passports, bounded authority, budget stops and signed receipts anyone can verify offline.
The problem
When an AI agent acts on the web or spends money, the other side has no way to know who sent it, what it may do, or to prove afterwards what happened.
What we engineered
Borrow from border control: identity documents, scoped permissions and a receipt for every crossing.
- A mission state machine with agent passports and child agents that inherit bounded authority.
- Budget hard stops and signed receipts with an offline verifier.
- An interactive Mission Lab that walks through admission, blocking and escalation scenarios.
How it connected
Standard HTTP message signatures (RFC 9421) in Python and TypeScript.
What technology was appropriate
Python and TypeScript monorepo.
Where it stands
Pre-alpha research. The Mission Lab demo is public; the code is not yet released.
Current state, stated as it is today.
See it yourself
Security, evaluation and governance
Security reviews, evaluation, audit trails and human approval where an action matters.
Build software
Custom web apps, internal tools, SaaS products and the APIs that connect them.
Bring us the bottleneck.
If your problem looks like one of these, tell us. We will say whether a build is the right answer.
Bring us a bottleneck