I've been building agents for a few months and the failure that scared me wasn't a crash, it was cost. An agent loops, every individual call looks fine, and you find out from the bill.
So I built a proxy that sits in front of the agent and stops it. Budget cap that cuts mid-stream, but also: it notices when the agent is sending the identical prompt over and over and breaks the loop before the call goes out, and it drops tool calls you've blocked (like delete_*) before they reach your code.
It's open source, runs locally, no signup:
https://github.com/gommapane1/SpendGuard
What I actually want to know: is this a real problem for you, or am I solving something I only had myself? And if you do guard against it, how?
Top comments (0)