REA: Reverse Engineer Anything
A tool that gives AI coding agents a consistent way to investigate how software works, from app behavior down to native binaries, so a feature can be understood, evidenced and rebuilt for another project.
REA gives an agent commands, skills and structured investigation workflows covering deep native analysis and function dossiers through Hopper or a user's own Ghidra on Linux, an experimental Windows x64 Ghidra path for approved native applications, execution-free managed binary triage, reproducible evidence records, controlled process capture, and passive observation of websites, Electron pages and related runtime debugging sessions, plus bounded JavaScript and source-map reconstruction. A versioned domain graph connects JavaScript application layers while keeping static inference distinct from runtime observation.
Its investigation model has three stages: decompiling an app to recover readable code, strings and names; following the code across the app until the agent can explain how a feature actually works; and recreating that understanding as a new feature adapted to the user's own stack, interface and requirements. Setup is a single command that installs an aligned MCP registration and a bundled routing skill together, after which a user simply describes the app and feature they want understood or rebuilt.