Awesome AI Agents › Runtime Analysis Tools
AiSOC is an open-source, self-hostable platform that automates the triage layer of a Security Operations Center. It ingests security telemetry from connected tools, normalizes it, and runs it through a rule library (reported at several thousand rules, with a smaller executable subset enabled by default) to detect and correlate findings into incidents rather than leaving analysts to review each alert individually. Each incident is then handed to an AI agent that investigates it, with every prompt sent to the model and every tool call the agent makes recorded for later audit, so the reasoning behind a verdict is inspectable rather than opaque. The agent produces a triage verdict with a confidence score and a rationale, and the system proposes a response action that a human must explicitly approve before anything is executed, keeping a human in the loop for any consequential action. When new threat intelligence arrives, AiSOC can re-sweep telemetry it already collected to see whether previously benign events now match a new indicator. The project ships with a local model bundled for the triage step, a cost dashboard that reports how many tokens the AI triage has spent, and a documented, from-scratch deployment walkthrough that brings the stack up on a single server against published container images. The maintainers publish an explicit "what is real" accounting of which screenshots and demos reflect live, unseeded runs against representative (not fabricated) event data versus illustrative material, which is unusual transparency for a security product demo. It is built primarily in Python with a web frontend, licensed MIT, and aimed at security teams that want an auditable, self-hosted alternative to closed SOC platforms, particularly ones wary of black-box AI triage decisions they cannot inspect or justify to auditors.
https://github.com/beenuar/AiSOC
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.