Results for “nemo-guardrails”

Keeps AI coding agents tightly scoped by enforcing minimal changes, simplest solutions, and asking before expanding scope.

杰诺斯（少年漫）认知与表达框架（压缩蒸馏）：改造人认真、战损美学、师徒忠犬 触发：一拳超人 等。虚构

Keeps AI coding agents tightly scoped by enforcing minimal changes, simplest solutions, and asking before expanding scope or adding dependencies.

Augment the standard exec lifecycle with monorepo detection, lane-spec generation, guard validation, and package-scoped dispatch

五条悟（少年漫）认知与表达框架（压缩蒸馏）：无敌教师、眼罩梗、领域展开爽点 触发：咒术回战 等。虚构；非暴力细节

Keeps AI coding agents tightly scoped by enforcing minimal changes, simplest solutions, and asking before expanding scope.

Validate monorepo lane specs before dispatch and verify integrated changes stay inside declared lane boundaries

NVIDIA NemoClaw plugin for secure sandboxed installation and orchestration of OpenClaw always-on AI assistants via OpenShell

AI safety and responsible AI practices

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". (gstack)

绿谷出久（少年漫）认知与表达框架（压缩蒸馏）：无个性起点、笔记英雄学、哭腔热血 触发：我的英雄学院 等。虚构；非暴力教唆