Awesome AI Agents › Runtime Analysis Tools
Agent Wiz is a Python command-line interface (CLI) tool designed for extracting, visualizing, and performing automated threat assessments on agentic workflows in AI systems. It supports a variety of popular AI agent orchestration frameworks such as LangGraph, AutoGen, CrewAI, AgentChat, LlamaIndex, n8n, OpenAI Agents, Pydantic-AI, Swarm, and Google-ADK. The tool is aimed at developers, researchers, and security teams who need to understand and secure complex large language model (LLM)-based agent workflows. The core functionality of Agent Wiz includes extracting agent workflows from source code using abstract syntax tree (AST)-based static parsing, visualizing the relationships and interactions between agents and tools in an interactive graph, and generating comprehensive security reports based on established threat modeling frameworks. Currently, it supports the MAESTRO threat modeling framework, which evaluates mission objectives, assets, entry points, security controls, threats, risks, and operational considerations to identify vulnerabilities and potential attack scenarios in AI agent systems. Agent Wiz provides a structured approach to mapping agent-to-agent and agent-to-tool interactions, making it easier to trace complex workflows without manual effort. The tool outputs standardized JSON graph representations of the workflows, which can be visualized as HTML-based interactive graphs. It also offers a simple CLI interface, an extensible software development kit (SDK), and clean JSON exports for integration with other tools. The project is open source and licensed under the Apache 2.0 License. It is actively maintained with plans to extend support to additional threat modeling frameworks such as STRIDE, PASTA, and LINDDUN, as well as to incorporate agent simulation-based threat exploration. Installation is straightforward via pip, and usage requires setting an OpenAI API key for some functionalities. Overall, Agent Wiz enhances visibility, structure, and security in AI agent orchestration by providing automated tools for workflow extraction, visualization, and threat assessment, helping teams to better understand and secure their AI systems.
https://github.com/Repello-AI/Agent-Wiz
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.