behavioral-safety

Here are 3 public repositories matching this topic...

sapiencallenmajin / TheSAPIENFramework

The SAPIEN Framework — an open standard (CC BY 4.0) for measuring AI behavioral safety (sycophantic drift), plus voigt-kampff, the FSL scoring CLI.

benchmark alignment red-team ai-safety blue-team drift-detection behavioral-safety ai-red-team llm-evaluation llm-safety ai-safety-research sycophancy-detection ai-blue-team

Updated Sep 7, 2026
Python

Tynapse / drift-sentry

Star

DriftSentry-4B behavioral-safety model training, evaluation, and benchmark toolkit

model-evaluation behavioral-safety llm-safety agent-safety

Updated Jul 31, 2026
Python

richard-porter / frozen-kernel

Star

A deterministic safety layer for probabilistic AI systems — preventing delusion reinforcement and AI-induced psychological harm through immutable governance

mental-health ai-safety ai-ethics ai-alignment guardrails responsible-ai behavioral-safety ai-governance sycophancy llm-safety human-ai-collaboration ai-accountability ai-psychosis deterministic-safety

Updated Mar 23, 2026
Go

Add this topic to your repo

To associate your repository with the behavioral-safety topic, visit your repo's landing page and select "manage topics."

Learn more