I woke up to a $40 bill from an agent that looped overnight on a $5 task. Every solution worked after the call. None stopped the TCP connection. baar-core checks your budget before every API call. Over cap → exception raised locally. No DNS. No TCP. $0 charged. → 84% cost reduction via semantic routing → Per-user SQLite quotas → LangGraph + FastAPI support → MIT licensed pip install baar-core
Hey PH! 👋
Happy to answer anything about how it works under the hood.
One thing I'm genuinely curious about how are you currently handling LLM cost control in your agents? Billing alerts? Hard limits on the provider side? Nothing yet?
I built baar-core because I couldn't find anything that worked *before* the API call. Would love to know if others hit the same wall or solved it differently.
AgencyHandy