agent-redteam is an open-source platform for red team security testing of AI agents, focusing on vulnerabilities such as prompt injection and LLM safety. It provides both a command-line interface and a dashboard for comprehensive evaluation and observability, targeting AI security researchers and developers.
agent-redteam is an Agent evaluation & testing project. It focuses on testing and evaluating the security of AI agents against prompt injection and other vulnerabilities. It is built as an open-source project for AI security researchers and developers. agent-redteam is open source under the MIT license. agent-redteam is available on the command line and the web, and it can be self-hosted.
agent-redteam first shipped in 2026. Among its 6 catalogued features are CLI interface, dashboard, and prompt injection testing.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do