Tencent/AI-Infra-Guard
AI-Infra-Guard by Tencent is a comprehensive AI Red Teaming platform offering intelligent vulnerability scanning, MCP server risk detection, and jailbreak evaluation to enhance AI security.
Awesome AI Agents › Red-Teaming Platforms
j3ssie/osmedeus
Osmedeus is an advanced and highly efficient orchestration engine tailored for security professionals, primarily focused on reconnaissance and penetration testing. Written in the Go programming language, it provides a robust framework for automating complex security workflows. The platform is designed to streamline various tasks involved in identifying vulnerabilities, mapping attack surfaces, and gathering intelligence during security assessments or bug bounty hunting. It acts as a central orchestrator, coordinating a multitude of security tools and scripts to perform tasks such as subdomain enumeration, port scanning, web application analysis, and OSINT (Open-Source Intelligence) gathering. Its architecture emphasizes modularity and scalability, allowing users to define custom workflows and integrate new tools seamlessly. Osmedeus aims to reduce manual effort and improve the speed and accuracy of security operations by providing an automated and configurable environment. While the project description does not explicitly mention AI or LLM capabilities, its nature as an 'orchestration engine' for complex security tasks positions it within the broader ecosystem of advanced workflow automation, which can often be augmented or integrated with AI-powered components for intelligent decision-making or data analysis in reconnaissance phases. Its utility extends across various phases of ethical hacking, from initial information gathering to vulnerability identification, making it a valuable asset for penetration testers and bug bounty hunters.
https://github.com/j3ssie/osmedeus
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.