j3ssie/osmedeus
Osmedeus is a powerful and modern orchestration engine designed for reconnaissance and penetration testing workflows, written in Go.
Awesome AI Agents › Red-Teaming Platforms
Tencent/AI-Infra-Guard
Tencent's AI-Infra-Guard (A.I.G) is a comprehensive AI Red Teaming platform designed to enhance AI security through intelligent vulnerability scanning and risk assessment. Developed by Tencent Zhuque Lab, A.I.G integrates multiple advanced capabilities including AI infrastructure vulnerability scanning, MCP server risk detection, and jailbreak evaluation for prompt security. The platform supports over 30 AI framework components and covers nearly 400 known CVE vulnerabilities, making it a robust tool for identifying security weaknesses in AI systems. It also features an AI-powered MCP server scan that detects nine major categories of security risks, supporting both source code and remote URL scanning. The jailbreak evaluation component rapidly assesses prompt security risks using curated datasets and enables cross-model security performance comparisons. A.I.G offers a modern, user-friendly web interface that allows one-click scanning with real-time progress tracking and generates comprehensive analysis reports. It supports multiple languages, including Chinese and English, and is compatible across Linux, macOS, and Windows platforms with Docker-based deployment options. The platform is open source and free under the MIT license, encouraging community contributions through an extensible plugin framework. Contributors can add new fingerprint rules, vulnerability scan rules, MCP security scan rules, and jailbreak evaluation datasets. The project is well-documented with online resources, user guides, and a contribution guide to facilitate community engagement. A.I.G aims to be the industry-leading AI red teaming platform by providing a thorough, intelligent, and easy-to-use solution for AI security risk self-examination, helping organizations safeguard their AI infrastructure against emerging threats.
https://github.com/Tencent/AI-Infra-Guard
Also in Red-Teaming Platforms
beclab/Olares
Olares is an open-source sovereign cloud operating system that enables users to run local AI models, manage personal data, and self-host various applications securely and privately on their own hardware.
GH05TCREW/pentestagent
Python terminal agent for AI-assisted penetration testing that drives nmap, sqlmap, a browser and MCP servers, with assist, autonomous agent, multi-agent crew and guided interactive modes.
larlarua/AutoCVE
Agent-driven platform that automates CVE discovery end to end, using multiple coordinated agents to audit source code, verify vulnerabilities, and generate submission-ready reports.
SanMuzZzZz/LuaN1aoAgent
LuaN1aoAgent v2 is an autonomous security research agent that splits work between Planner, Executor and Observer roles and records every conclusion as evidence-backed nodes in a causal reasoning graph.
qualifire-dev/rogue
Client-server platform for evaluating and red-teaming AI agents over A2A, MCP or direct Python calls, with 75+ vulnerabilities, 20 attack techniques and compliance-framework reporting.
ASCIT31/Dark-Moon
Open-source autonomous penetration testing platform where specialised agents plan and run real offensive operations through a controlled MCP execution layer, with local tokenization that hides sensitive values from the model.
hackerai-tech/hackerai
An open-source penetration testing assistant with a chat interface and an agent mode that executes security tooling inside isolated cloud sandboxes on a durable task runtime.