Awesome AI Agents › Runtime Analysis Tools
Rogue is an advanced automated web vulnerability scanner that leverages Large Language Models (LLMs) such as OpenAI and Anthropic Claude to intelligently discover and validate security weaknesses in web applications. Unlike traditional scanners that rely on predefined patterns, Rogue mimics the thought process of a human penetration tester by analyzing application behavior, generating sophisticated test payloads, and autonomously validating findings to reduce false positives. The tool is designed to provide comprehensive security testing by understanding the context of the target application and adapting its testing strategy accordingly. Key features of Rogue include intelligent vulnerability discovery, advanced payload generation tailored to the target, context-aware testing that analyzes application responses, automated exploit verification, and detailed reporting with reproduction steps. It also supports optional subdomain enumeration, recursive testing of discovered URLs, and built-in proxy traffic monitoring to capture and analyze all web traffic during scans. Rogue is built with a modular architecture comprising components such as an agent to orchestrate scanning, a planner that uses LLMs to generate testing strategies, a scanner for web interaction and data collection, a proxy for network traffic monitoring, a reporter for generating detailed vulnerability reports, and a suite of testing and exploitation tools. It supports multiple LLM providers and models, allowing users to choose between OpenAI and Anthropic Claude models for their scans. The project is in an early release stage with ongoing development and welcomes open-source contributions. It requires Python 3.8+, API keys for OpenAI and optionally Anthropic, and Playwright for web automation. Rogue emphasizes ethical use and security best practices, advising users to obtain proper authorization before testing. Overall, Rogue represents a cutting-edge approach to automated web security testing by integrating AI-driven intelligence to enhance the accuracy, depth, and adaptability of vulnerability scanning processes.
https://github.com/faizann24/rogue
PrivateGPT is a fully private, offline-capable AI platform that enables users to interact with their documents using Large Language Models through a comprehensive API and user-friendly interface, ensuring data never leaves the user's environment.
PentAGI is a fully autonomous AI-driven penetration testing system that integrates professional security tools, multi-agent AI collaboration, and scalable microservices architecture to deliver comprehensive and automated security assessments.
Impacket is a Python library offering low-level programmatic access and implementations for various network protocols, focusing on security research and educational use.
VIPER is a versatile and powerful red team platform that supports adversary simulation and cybersecurity assessments across multiple operating systems, enhanced with AI-driven automation and extensive post-exploitation capabilities.
MCP-Scan is a security tool that statically and dynamically scans MCP connections to detect and prevent vulnerabilities like prompt injections, tool poisoning, and cross-origin escalations, offering real-time monitoring and customizable guardrails for enhanced protection.
OpenRecall is a fully open-source, privacy-focused digital memory tool that captures and makes searchable your digital history through screenshots, supporting Windows, macOS, and Linux with local data storage and advanced semantic search capabilities.
MCP server that exposes Cheat Engine memory reading, scanning, disassembly and debugging to AI agent clients through roughly 180 tools over a named pipe or TCP relay.
Amon is a modern, open-source server monitoring platform designed to help users track and manage server performance and uptime effectively.