Updated 10 months ago

doomarena • Science 36%

DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats

Updated 10 months ago

promptfoo • Science 26%

Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

Updated 10 months ago

https://github.com/amazon-science/turbofuzzllm • Science 26%

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice