How I stopped surprise $40+ LLM bills from agent loops (pre-call hard limits)

I woke up to a nasty bill because an agent looped overnight. All the usual tools (alerts, soft budgets) only reacted after the damage was done. So I built baar-core: lightweight library that checks budget before every API call. Raises exception locally No DNS, no TCP → $0 charged on overrun Semantic routing (84% savings) Per-user SQLite quotas Just launched on Product Hunt: https://www.producthunt.com/post... Open source: pip install baar-core Would love feedback from anyone running agents or multi-tenant LLM apps in production.