Download
REA (Reverse Engineer Anything) is an open-source, AI-powered reverse engineering toolkit that enables developers and AI agents to analyze software applications, native binaries, and runtime behavior. The platform uses the Model Context Protocol (MCP) to connect AI coding assistants with tools for inspecting compiled code, application structures, and software functionality. It supports reverse engineering of native executables, JavaScript and Electron applications, .NET assemblies, Android APKs, WebAssembly modules, firmware, and websites. REA integrates with reverse engineering tools such as Ghidra, Hopper, and IDA to examine assembly instructions, decompiled pseudocode, symbols, functions, and code references. Developers can use the platform to investigate how software features work, trace application behavior, identify implementation details, and reconstruct functionality in their own projects. REA supports AI coding assistants including Claude Code, Codex, Cursor, Gemini CLI, etc.
Features
- AI-Powered Reverse Engineering: Use AI agents to investigate software functionality, analyze application behavior, and reconstruct features from existing applications without requiring source code.
- Native Binary Analysis: Examine compiled executables using Ghidra, Hopper, or IDA to retrieve pseudocode, assembly instructions, symbols, function calls, and code references.
- Multi-Platform Application Inspection: Analyze JavaScript, Electron, .NET, Android APKs, WebAssembly, firmware, websites, and other software artifacts.
- MCP Integration: Connect reverse engineering capabilities to Claude Code, Codex, Cursor, Gemini CLI, Grok Build, and other MCP-compatible AI agents.
- Runtime and Behavioral Analysis: Inspect application processes, browser interactions, network activity, crash records, and execution behavior to understand how software operates.
- - Command-Line Automation and Evidence Tracking: Run reverse engineering tasks through CLI commands, generate structured analysis results, and review supporting evidence and limitations behind findings.
Project Samples
