agent-budget-semantics: Differential testing of budget enforcement across 11 AI agent frameworks

agent-budget-semantics is an open-source differential testing project that runs identical tasks across 11 AI agent frameworks to compare how each enforces token and cost budgets. Discrepancies in budget handling can cause unexpected overruns in production pipelines. The project documents the variance and provides a reusable test harness for benchmarking budget semantics across frameworks.