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
ASCIT31/Dark-Moon
DarkMoon is a GPL-3.0 platform that automates penetration testing by orchestrating AI agents over a suite of real offensive security tools. The agent layer reasons about a target, plans an assessment, and coordinates specialised agents for distinct attack surfaces, including web applications, Active Directory, Kubernetes, network services and content management systems. A central design decision is that the model never executes anything itself: all actions are issued through a controlled Model Context Protocol interface that fronts more than fifty integrated tools such as Nuclei, NetExec, BloodHound, sqlmap, Naabu, httpx and ffuf, which keeps the set of possible operations bounded and auditable. The second design decision is a privacy gateway based on reversible local tokenization. IP addresses, hostnames, domains, URLs, email addresses, credentials and internal paths are replaced with deterministic placeholders before any prompt reaches the language model; the real values are substituted back locally at the moment a tool runs and masked out again in every result, so sensitive infrastructure data does not leave the perimeter, and attempted exfiltration through the model is blocked. This makes it possible to use a hosted model under data sovereignty constraints, and the project also supports running entirely on a local model through Ollama or llama.cpp. Findings are backed by proof of exploitation rather than signature matches, and reports are generated automatically in a structured, evidence-based form with attack path analysis. The project positions itself for continuous use, including running assessments after a build in a CI/CD pipeline so that critical issues surface before production. A companion benchmarks repository documents a black-box run against OWASP Juice Shop, reported as 57 findings in about 28 minutes on a local model, together with a comparison against other autonomous pentesting projects. Intended users are security teams, DevSecOps engineers and penetration testers.
https://github.com/ASCIT31/Dark-Moon
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.
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.