Awesome AI Agents › Runtime Analysis Tools
PentAGI is a fully autonomous AI agent system designed for complex penetration testing tasks. It leverages advanced artificial intelligence technologies to automate security testing processes, making it a powerful tool for information security professionals, researchers, and enthusiasts. The system operates within a secure and isolated sandboxed Docker environment, ensuring safe execution of penetration tests. PentAGI integrates over 20 professional pentesting tools such as nmap, metasploit, and sqlmap, providing a comprehensive suite for vulnerability assessment and exploitation. The system features a smart memory system that stores research results and successful approaches for reuse in future tasks, enhancing efficiency and learning capabilities. It includes a built-in web intelligence component with an isolated browser for gathering the latest information from web sources. Additionally, it integrates with multiple external search APIs like Tavily, Traversaal, Perplexity, DuckDuckGo, and Google Custom Search to enrich its data collection. PentAGI employs a team of specialized AI agents that delegate tasks among research, development, and infrastructure roles, enabling a collaborative and multi-agent approach to penetration testing. The architecture supports detailed monitoring through logging and integration with Grafana and Prometheus for real-time system observation. It generates detailed vulnerability reports complete with exploitation guides, aiding security professionals in understanding and mitigating risks. The system uses smart container management to automatically select Docker images based on task requirements and offers a modern, user-friendly web interface for management and monitoring. It supports REST and GraphQL APIs for seamless integration with external systems and ensures persistent storage of commands and outputs in PostgreSQL with the pgvector extension. Designed with scalability in mind, PentAGI features a microservices-based architecture that supports horizontal scaling. It is a self-hosted solution, giving users full control over deployment and data. The system supports flexible authentication with various large language model providers including OpenAI, Anthropic, Deep Infra, OpenRouter, and DeepSeek. Deployment is streamlined through Docker Compose with comprehensive environment configuration, making it quick and easy to set up. Overall, PentAGI represents a cutting-edge, autonomous penetration testing platform that combines AI, professional tools, and scalable architecture to deliver an advanced security testing solution.
https://github.com/vxcontrol/pentagi
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.
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.
Cisco AI Defense security scanner that inspects MCP servers, tools, prompts and resources for malicious behavior using YARA rules, an LLM-as-a-judge engine and the Cisco AI Defense inspect API.