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
Red-Teaming Platforms
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.
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.
westonbrown/Cyber-AutoAgent
Autonomous penetration testing agent built on the Strands framework that plans and runs security assessments against a target, selects tools dynamically and stores evidence in a persistent memory backend.
Stanford-Trinity/ARTEMIS
Autonomous red teaming engine from the Stanford Trinity project in which an LLM supervisor spawns and coordinates multiple Codex sub-agents to discover vulnerabilities and solve capture-the-flag challenges.
ARCANGEL0/EVA
EVA (Exploit Vector Agent) is a Python command-line LLM agent that guides a penetration test end to end, proposing attack strategy, generating the next commands and analysing their output across recon, exploitation and post-exploitation.
deonmenezes/mantishack
Autonomous vulnerability-discovery agent built as a fork of the OpenAI Codex CLI, running a staged recon, detection, reachability and attacker-simulation pipeline over a codebase with findings owned by MCP tool servers.
lasso-security/mcp-gateway
MCP Gateway is a plugin-based intermediary solution that orchestrates multiple MCP servers, providing centralized management, security guardrails, and a unified interface for AI infrastructure.