Awesome AI Agents › Runtime Analysis Tools
GhidraGPT is a Java extension for the Ghidra reverse engineering suite that brings large language models into the decompiler workflow. The user right-clicks a function in either the Decompiler or the Listing view and picks an action from a GhidraGPT submenu; the plugin sends that function's current decompiled C to the configured model provider and streams the reply token by token into a dedicated console panel. Three actions are available. Explain produces a natural-language summary of what the selected function does, derived only from its decompiled code. Rewrite recovers a descriptive function name, renames local variables and parameters, infers their types, updates the function prototype and adds inline comments, then writes that markup back into the Ghidra program database so the improvements persist in the project. Audit reviews the decompiled function for likely security defects such as unbounded copies, integer overflows and unchecked return values. The documentation is explicit that every action works on one function at a time using its decompiler output as the only context, with no interprocedural or whole-program analysis, and that Audit findings are best-effort model output without cross-function dataflow or call-graph awareness, to be treated as leads for verification rather than as sound static analysis. Providers are pluggable and selected from a configuration panel, with live model listing for most of them: OpenAI, Anthropic, Google Gemini through its OpenAI-compatible endpoint, Cohere, Mistral, DeepSeek, xAI Grok, OpenRouter, local Ollama models needing no key, and any custom OpenAI-compatible endpoint. Model, temperature, maximum tokens and request timeout are all adjustable. The extension is built with Maven against a local Ghidra installation and installed as a zip through Ghidra's extension manager; it targets Ghidra 12.1.x. API keys are stored locally in a config file with XOR obfuscation, which the README states is not real encryption.
https://github.com/weirdmachine64/GhidraGPT
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.