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
hackerai-tech/hackerai
HackerAI is a self-hostable web application that acts as an assistant for penetration testing and offensive security work. The stack is TypeScript with Next.js and React on the front end and Convex as the database and backend, with authentication and user management handled by WorkOS. Model access is routed through OpenRouter, and a separate OpenAI key is used for content moderation on inputs and outputs. The distinguishing feature is agent mode, in which the agent loop does not run in the request handler but as a durable task on Trigger.dev, so long security assessments survive restarts and can be resumed. Commands the agent issues are executed away from the host machine in isolated cloud environments, with E2B sandboxes or AWS Lambda microVMs as the two supported providers, which keeps tooling execution contained. Several capabilities are optional and enabled by adding provider keys: Perplexity for web search during reconnaissance, Jina AI Reader for retrieving page content from URLs, Amazon S3 as an alternative to Convex file storage, Redis for resuming interrupted response streams, Upstash Redis for rate limiting, PostHog for analytics and Stripe for payment processing in a hosted deployment. Local development runs the Next.js server, the Convex development server and a Trigger.dev worker, with environment variables for the worker configured in the Trigger.dev dashboard rather than on the web host, and the repository documents branch-routed workers for parallel local agents. The project is released under an Apache 2.0 licence carrying commercial restrictions and is also offered as a hosted service. It is aimed at security professionals and researchers who want an agent that can run reconnaissance and exploitation tooling under their own keys and infrastructure rather than through a closed product.
https://github.com/hackerai-tech/hackerai
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.