{"id":"deepteam","name":"DeepTeam","maker":"Confident AI","url":"https://github.com/confident-ai/deepteam","repo":"confident-ai/deepteam","package":"pypi:deepteam","summary":"An open-source Python framework for red teaming LLMs and agents against vulnerabilities and attack methods.","details":"Simulates adversarial attacks such as prompt injection and jailbreaks against a model or agent callback, and scores the results across vulnerability categories. It is built by the makers of DeepEval and is released under Apache 2.0.","open_source":true,"hosted":false,"also":["observability"],"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/deepteam","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true,"repository":{"at":"2026-11-15T20:20:00.691Z","archived":false,"licence":"Apache-2.0","language":"Python","last_change":"2026-10-23T11:32:04.000Z","latest_release":{"tag":"v1.0.9","published":"2025-11-12T14:18:25.000Z"}}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}