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
larlarua/AutoCVE
AutoCVE is an agent-driven platform that automates the full CVE-hunting workflow, from selecting projects and importing repositories through creating audit tasks, running agent-based vulnerability discovery, and generating CVE submission reports. Its stated goal is that a user only needs to copy the generated report content and submit it to complete a CVE application. The system uses a multi-agent architecture in which an Orchestrator coordinates Recon, Scan, Triage, Finding, and Verification agents to collaboratively handle information gathering, tool-based scanning, false-positive filtering, deep vulnerability mining, and dynamic verification, then merges and finalizes results. It offers three audit modes: an enhanced-scan mode chaining Scan and Triage for fast analysis and false-positive filtering, an intelligent-audit mode driven by the Finding agent for deep discovery of high-value vulnerabilities suited to CVE and zero-day research, and a comprehensive mode combining tool scanning with source analysis for full coverage. The Finding agent, purpose-built for CVE scenarios, analyzes project source directly using a ReAct loop, specialized tool calls, nudge corrections, and a structured FinalizeFinding termination mechanism to produce vulnerabilities meeting CVE-application criteria. Interactive auditing lets users continue questioning results within a session context, and a visualization layer shows activity logs, an agent tree, tool calls, stage progress, and audit conversations. Discovered vulnerabilities are auto-submitted by agents, deduplicated, and stored in a vulnerability-management module, with per-agent Skills configuration to extend capabilities. Built with a FastAPI backend, React frontend, and PostgreSQL, it deploys via a single Docker command. The maintainers report thirty CVEs found across fourteen open-source projects in a one-week test. It targets security researchers and source-code auditors.
https://github.com/larlarua/AutoCVE
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.
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.