Stars
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we confi…
Multi-platform, free open source software for visualization and image computing.
DeepTeam is a framework to red team LLMs and AI agents.
A repository for your Garak runs, as well as a modern visualizer.
MagMueller / stargazers
Forked from spencerkimball/stargazersAnalyze GitHub stars
leondz / garacc
Forked from NVIDIA/garakthe LLM vulnerability scanner
A quick guide (especially) for trending instruction finetuning datasets
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command li…
An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
A tool to scan websites for chatbot functionality
Distributed Asynchronous Hyperparameter Optimization in Python
🐍 Python library for the generation of random text that looks like Latin
aiki-extension / Aiki
Forked from Shuckdubbie/Distraction-ShieldProtect your attention and stay focused ⚡️
A LLM explicitly designed for getting hacked
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
[AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts
A Python module for getting the GPU status from NVIDA GPUs using nvidia-smi programmically in Python
Make your GenAI Apps Safe & Secure 🚀 Test & harden your system prompt
Implementation of BEAST adversarial attack for language models (ICML 2024)
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.