NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
-
Updated
Apr 16, 2026 - Python
#
safety
Here are 398 public repositories matching this topic...
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
reinforcement-learning transformers transformer safety llama gpt datasets beaver alpaca ai-safety safe-reinforcement-learning vicuna deepspeed large-language-models llm llms rlhf reinforcement-learning-from-human-feedback safe-rlhf safe-reinforcement-learning-from-human-feedback
-
Updated
Nov 24, 2025 - Python
List of resources about programming practices for writing safety-critical software.
-
Updated
Mar 11, 2025 - Python
Open-source vulnerability disclosure and bug bounty program database
legal data hackers bug-bounty safety simplicity responsible-disclosure safe-harbor-framework security-research vulnerability-disclosure disclosure-policy bug-bounty-hunters
-
Updated
Mar 28, 2026 - Python
[EMNLP 2024 Demo] MarkLLM: An Open-Source Toolkit for LLM Watermarking
-
Updated
Mar 17, 2026 - Python
PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
control reinforcement-learning quadcopter robotics symbolic gym cartpole safety quadrotor robustness pybullet casadi
-
Updated
Nov 6, 2025 - Python
面向中文大模型价值观的评估与对齐研究
-
Updated
Jul 20, 2023 - Python
Decrypted Generative Model safety files for Apple Intelligence containing filters
-
Updated
Jan 26, 2026 - Python
A collaborative collection of open-source safe GPT-3 prompts that work well
-
Updated
Mar 12, 2022 - Python
Official datasets and pytorch implementation repository of SQuARe and KoSBi (ACL 2023)
-
Updated
Jun 29, 2023 - Python
Safe reinforcement learning with stability guarantees
-
Updated
Feb 8, 2022 - Python
AutoHarness: Automated Harness Engineering for AI Agents
audit multi-agent safety governance ai-agents tool-use agent-framework llm prompt-injection context-management harness-engineering
-
Updated
Apr 2, 2026 - Python
Official Implementation of the CKA-Agent, "The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search".
-
Updated
Jan 31, 2026 - Python
[arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
-
Updated
Feb 20, 2024 - Python
A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)
benchmark privacy toolbox safety multi-modal fairness robustness claude gpt-4 trustworthy-ai truthfulness mllm
-
Updated
Jun 27, 2025 - Python
Safe Bayesian Optimization
-
Updated
Nov 14, 2022 - Python
Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"
safety llama representation language-model mistral explainable-ai hallucination baichuan hallucinations gpt-4 truthfulness llm llms chatgpt chatglm llm-inference llama2 llama3
-
Updated
Mar 26, 2024 - Python
How good are LLMs at chemistry?
-
Updated
Jan 26, 2026 - Python
Improve this page
Add a description, image, and links to the safety topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the safety topic, visit your repo's landing page and select "manage topics."