IBM/ares

LLM Adversarial Robustness Toolkit, a toolkit for evaluating LLM robustness through adversarial testing.

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision evaluations, and synthesizing validated guardrails for safe self-improvement.

Break your AI before they do. Join Discord: https://discord.gg/NXXz8JG74

Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

DeepTeam is a framework to red team LLMs and AI agents.

AI / LLM Red Team Field Manual & Consultant’s Handbook

Toolbox to run adversarial attacks against LLM.

the LLM vulnerability scanner

LLM security testing framework for detecting prompt injection, jailbreaks, and adversarial attacks — 190+ probes, 28 providers, single Go binary