About
One person builds this. That is worth knowing before you put it in front of a production loop.
Why it exists
Provider spend caps are monthly and per vendor. They tell you about the money after the month that spent it. An agent loop does its damage in an evening, across whichever providers the job happens to touch, and a cap that resets tomorrow does not stop the run that is going now.
So the ceiling here is attached to a job rather than to a calendar. Every
call that carries the same task_ref draws down
one budget, whatever the provider, and the call that would break it does
not go out.
What it deliberately is not
It is not a proxy. Your traffic does not route through anything of ours and we never hold your provider keys. It does not read your provider bill, and it does not convert the units you pass into money. It will not tell you what a call cost; it will stop the one that would cost too much, on the number you gave it.
Who is behind it
AgentBill is built and run by Lior Cohen. There is no team, no support rota, and no queue: mail goes to a person who reads it. If that matters to your risk assessment either way, it should, and it is why the page says so instead of writing "we" everywhere.
That is also the whole argument for the ceiling. One person cannot watch a loop at three in the morning, so the ceiling has to be the thing that does.
Where it is
The server, both SDKs and this website are one open repository. The mechanism this page describes is a few hundred lines of it, and you can read the ones that matter rather than take the description on trust.