AI testing & safety
Check that AI apps give good answers, follow safety rules and resist trick instructions.
9 projects, highest rated first.
Promptfoo
Tests AI apps and chatbots to check their answers are good and that they can't be easily tricked.
AI testing & safetyAdversarial Robustness Toolbox (ART)
A Python toolkit for testing how AI models hold up against attacks, and for defending them.
AI testing & safetyNeMo Guardrails
NVIDIA's toolkit for adding safety rules that keep AI chatbots on topic and guard against misuse.
AI testing & safetyA.I.G (AI-Infra-Guard)
A security testing platform that scans AI agents, tools and servers for weaknesses.
AI testing & safetygarak
A scanner from NVIDIA that tests AI chatbots for weaknesses like jailbreaks, data leaks and harmful output.
AI testing & safetyGuardrails
A Python library that checks what goes into and comes out of AI models to catch problems and risks.
AI testing & safetyGiskard
A Python library for testing AI agents and chatbots for quality, safety and weak spots.
AI testing & safetyFailproof AI
Watches what AI agents do on your computer and blocks risky actions before they happen.
AI testing & safetySuperagent SDK
Helps developers protect AI apps from trick instructions, data leaks and harmful outputs.