We built NORNR for teams running agent workflows that are getting close to real spend on APIs, compute, or vendor actions.
A lot of the hard part is not whether an agent can pay. It is whether the spend should happen at all, under what mandate, and with what evidence afterward.
That is what NORNR is for.
It sits between intent and settlement and adds:
- mandates
- approvals
- budget controls
- audit trail
We think this becomes especially relevant once LangGraph-style or multi-step agent workflows start touching real budgets and external counterparties.
What is live today:
- quickstart: https://nornr.com/quickstart
- control room: https://nornr.com/app
- repo: https://github.com/Onechan/NORNR
Curious whether anyone here is already dealing with approval thresholds, counterparty controls, or auditability around agent spend.