DeepTeam
Confident AIAn open-source red-teaming framework for LLM systems from Confident AI. It simulates adversarial attacks (jailbreaking, prompt injection, multi-turn exploitation) with 50+ built-in vulnerability checks and 20+ attack methods aligned to OWASP Top 10 for LLMs, NIST AI RMF, and MITRE ATLAS, and ships production guardrails.
DeepTeam, Apache-2.0, Confident AI; ~1.9K GitHub stars (June 2026). 50+ vulnerability checks, 20+ attack methods; OWASP/NIST/MITRE aligned. Verified live June 2026.
Openness
5 high confidence- license
- Apache-2.0(OSI)
- source
- public
- self-host
- yes
- service
- none
- core-gated
- ungated
Fully open source: Apache-2.0 red-teaming framework, self-hostable.
- https://github.com/confident-ai/deepteam recorded 2026-06-29
Apache-2.0; ~1.9k stars; 50+ vuln checks, 20+ attacks; OWASP/NIST/MITRE aligned
Adoption
2 low confidence~1.9K GitHub stars (June 2026); stars-only proxy, capped per methodology.
- https://github.com/confident-ai/deepteam recorded 2026-06-29
~1.9k stars (June 2026)
Capability
4 medium confidenceStrong standards alignment (OWASP/NIST/MITRE) and broad attack coverage; also ships runtime guardrails.
- https://github.com/confident-ai/deepteam recorded 2026-06-29
50+ vulnerabilities, 20+ attacks, OWASP/NIST/MITRE
Unchanged since 2026-08-01 (last edited, not re-checked)