DeepTeam: Open-source framework for red teaming LLMs locally

tom_doerr · x · 2026-09-19

DeepTeam is an open-source red teaming framework for LLM systems (2.8k stars on GitHub) — think penetration testing, but for LLMs.

It runs locally and simulates attacks including jailbreaking, prompt injection, and multi-turn exploitation to uncover vulnerabilities like bias, PII leakage, and SQL injection in AI agents, RAG pipelines, and chatbots. It also offers guardrails to prevent these issues in production.

Built on DeepEval (the open-source LLM evaluation framework) and maintained by Confident AI, with an accompanying platform for managing risk assessments and sharing reports.

Original post →

More from coding & agent

coding & agent channel →