DeepTeam

What DeepTeam is

DeepTeam is an open-source Python framework for red teaming large language model systems. It provides more than 50 ready-to-use vulnerability checks covering areas such as bias, toxicity, personal-information leakage, prompt leakage, and security risks. Adversarial simulations include jailbreaks, prompt injection, automated evasion, data extraction, and response manipulation. DeepTeam evaluates outputs with vulnerability-specific LLM-as-a-Judge metrics that return a binary result and reasoning. Supported reference frameworks include OWASP, NIST AI RMF, MITRE ATLAS, the EU AI Act, BeaverTails, and Aegis. The listed model providers include OpenAI, Claude, Gemini, Azure OpenAI, AWS Bedrock, Vertex AI, Mistral, LiteLLM, and Portkey. CI/CD listings include GitHub Actions, GitLab CI, Jenkins, CircleCI, Buildkite, and Azure Pipelines. Installation uses a Python virtual environment and pip. A prepared dataset is not required because attacks are generated dynamically. Results can remain local or be sent to Confident AI for centralized viewing and production red teaming through a user interface. DeepTeam is Apache 2.0 licensed and supports self-hosted deployment.