https://pypi.org/project/agentanvil/ Recent updates to the Python Package Index for agentanvil en https://pypi.org/project/agentanvil/0.1.1/ Contract-based testing framework for LLM agents — hybrid metrics (objective + LLM-as-judge + human), multi-agent and A2A protocol support, deterministic record/replay envelope. Wed, 29 Apr 2026 18:57:17 GMT https://pypi.org/project/agentanvil/0.0.1/ Testing and evaluation platform for LLM agents — hybrid metrics, multi-agent simulation, and iterative prompt improvement. Fri, 17 Apr 2026 16:38:01 GMT