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
GH05TCREW/pentestagent
PentestAgent is an open-source penetration testing assistant written in Python that wraps a large language model in a terminal user interface and gives it direct access to offensive security tooling. It requires Python 3.10 or newer and an API key for OpenAI, Anthropic or any other provider supported by LiteLLM, and it can be pointed at OpenAI-compatible or Anthropic-compatible relay endpoints through base-URL environment variables. The interface exposes four operating modes: assist for a single instruction with tool execution, agent for autonomous execution of one task, crew for a multi-agent setup where an orchestrator spawns specialised workers, and interact for guided chat during an engagement. Slash commands set the target, list tools, show notes, generate a report from the session, inspect token and memory usage, browse and restore saved conversations, and manage MCP servers. Built-in tools cover a terminal, a Playwright-driven browser, a notes store, web search through Tavily, and spawn_mcp_agent, which lets a running agent start a child copy of itself as a subordinate MCP server over stdio. The child process gets its own runtime, LLM client, conversation history and notes store, and its complete tool set is injected back into the parent, so hierarchical delegation works without any external orchestration layer. Tools can be executed inside Docker for isolation, using either a base image with nmap, netcat and curl or a Kali image carrying metasploit, sqlmap and hydra. Prebuilt attack playbooks describe structured approaches to specific black-box assessments and are run from the command line against a named target. The project is aimed at security testers who want a model to plan and drive standard command-line and browser tooling while keeping session notes and producing a report.
https://github.com/GH05TCREW/pentestagent
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.
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.