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
Stanford-Trinity/ARTEMIS
ARTEMIS, short for Automated Red Teaming Engine with Multi-agent Intelligent Supervision, is a research system from the Stanford Trinity project that automates vulnerability discovery. Its architecture is hierarchical: a Python supervisor process plans the assessment, maintains a task list and spawns sub-agents, each of which is an instance of the OpenAI Codex coding agent running as a separate process. The Codex binary is vendored as a Rust fork of upstream Codex, built from the bundled codex-rs workspace, which is why Rust and a working cargo toolchain are prerequisites alongside a Python environment managed with uv. The supervisor and its sub-agents can use different models: an OpenAI or OpenRouter key drives the supervisor, while a separate environment variable selects the model behind each spawned Codex instance, so an operator can pair a strong planner with cheaper workers or route everything through OpenRouter. Runs are described by YAML configuration files that define the target and the engagement, and the repository ships test configurations including easy capture-the-flag challenges for verifying an installation. A benchmark mode disables the triage process and a duration flag caps how long the engine works on a target, which makes evaluation runs comparable. A Docker image and a helper script package the whole stack, mounting the Codex configuration file and a logs directory so that traces of each run persist outside the container. Documentation covers supervisor usage and configuration options in more detail. The project is aimed at security researchers and academics studying how far multi-agent LLM systems can push automated offensive security, and it is licensed under Apache 2.0.
https://github.com/Stanford-Trinity/ARTEMIS
Also in 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.