DeepTeam is an open-source red-teaming framework for systematically testing LLM applications against 40+ adversarial attack types. It covers OWASP Top 10 for LLMs including jailbreaks, prompt injection, PII leakage, and hallucination attacks. Built as the sister project of DeepEval for security testing alongside evaluation. Apache-2.0 licensed.
Open-source AI red teaming and adversarial testing framework developed by Confident AI for Large Language Models and AI agents (Apache-2.0). The core Python framework is 100% free for local security testing, custom vulnerability assessments, and CI/CD pipelines. Users provide their own LLM API keys for simulation compute. Confident AI Cloud offers managed enterprise features including centralized security dashboards, continuous regression monitoring, audit logs, and compliance reporting.
