dreadnode/AIRTBench-Code

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.

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

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

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

AI Red Teaming playground labs to run AI Red Teaming trainings including infrastructure.

Agent Security Bench (ASB)

Open-source adversary emulation for AI agents and MCP servers.

AI Robustness Evaluation System