A Pi coding agent extension that uses TypeSafe Jev to gate tool calls and judge outputs. Includes a shadow/enforce tool-call gate, output leak/failure detection, and a jev_ask tool for typed answers. Calibration results are documented.
该仓库是 Pi 编码代理的扩展，深度集成 TypeSafe Jev：实现了工具调用门控、输出泄露/失败检测、jev_ask 工具，并提供了详细的配置、命令和校准实验数据，是真实的使用与测试。
NyarlathotepppppNyarlathoteppppp/pi-heedRuntime constraints for the pi coding agent: checks every side-effecting tool call against user-stated rules, powered by TypeSafe Jev. Includes a detailed benchmark and experiment log evaluating Jev's System One decisions.
cwjechw98-langcwjechw98-lang/jev-gatesThree guardrail gates for coding agents: pre-action approval, evidence-based completion, and rubric regression checks, powered by TypeSafe Jev (System One). Includes CLI scripts, offline tests, and CI workflows.
InverxInverx/JevREJevRE is a Python CLI integrating TypeSafe AI's Jev System One model to recommend the next investigation step in Android reverse engineering. It includes a real Jev API client and an offline mock mode.
