safety

11 projects share this GitHub topic

Lines connect members that are measurably related to each other. Dot size reflects stars.

🧬 Members

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based…

destructive_command_guard

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by…

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Awesome-Jailbreak-on-LLMs

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It…

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka…

[EMNLP 2024 Demo] MarkLLM: An Open-Source Toolkit for LLM Watermarking

safe-control-gym

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based…

Awesome-LLM-Uncertainty-Reliability-Robustness

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

Safe-Reinforcement-Learning-Baselines

The repository is for safe reinforcement learning baselines.

AutoHarness: Automated Harness Engineering for AI Agents

🔗 Related families

security 110 jailbreak 12 privacy 61 vlm 69 safe-reinforcement-learning 4 robustness 8 guardrails 18 llm-security 27

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.