sahiljagtapyc

AgentBudget — I got a $32 surprise bill from a runaway AI agent, so I built a real-time kill switch

A few weeks ago I left an AI agent running, walked away for 20 minutes, and came back to a bill I didn't expect. I searched for a tool that could just stop the agent when it hit a dollar limit. Nothing existed. So I built AgentBudget. It monkey-patches the OpenAI and Anthropic SDKs, tracks running cost per API call, and throws a BudgetExceeded exception the moment the agent crosses its limit. Under 2ms overhead. One import, one line. from agentbudget import BudgetManager budget = BudgetManager(max_cost="$5.00") That's it. Works with OpenAI, Anthropic, Gemini, Mistral, Cohere, LangChain, and CrewAI. Would love feedback from people building agents in production — especially around what the cloud dashboard should look like.

GitHub: github.com/sahiljagtap08/agentbudget

Thanks! That's awesome - love that the Twitter thread connected here. Let me know how the integration goes, happy to help if you hit any issues. What are your agents running on?

interesting

I wonder if this is less about “bad posture” and more about how people unconsciously optimize for stability when thinking deeply. When I’m reasoning through something hard, I tend to lock into whatever position minimizes micro-adjustments - even if it looks terrible ergonomically.

damnn