CODE · Coding & Dev
Empower AI Coding Agents with Autonomous Binary Reverse Engineering & Decompilation via REA
A jaw-dropping viral sensation with 360k+ stars on GitHub! REA (Reverse Engineering Agent) gives Claude Code, Codex, and Cursor native decompilation and binary disassembly superpowers. Backed by headless Ghidra, Tree-sitter, and control flow graph (CFG) synthesizers, it inspects closed-source Windows PE, Linux ELF, and Electron packages to decode proprietary protocols, reconstruct obfuscated algorithms, and audit security flaws.
CORE TOOLS
REA (Open Source), Ghidra, Tree-sitter, Claude Code / Codex, Model Context Protocol (MCP)
BEST FOR
Security researchers, reverse engineers, systems programmers, open-source clean-room contributors, protocol analysts
REQUIREMENTS
Python 3.10+, Java 17+ (for headless Ghidra), target binary file, and an MCP-capable coding assistant (Claude Code, Cursor).
✦ WHY THIS WORKFLOW
Manual binary reverse engineering demands tedious hours tracing disassembly and call trees. REA merges headless Ghidra primitives with LLM reasoning, transforming cryptic assembly into clear architecture diagrams and clean-room implementations.
✦
Interactive Workflow Animation Preview
Step-by-Step Action Checklist
0 / 4 Completed
READY-TO-USE PROMPT TEMPLATE
I am conducting a clean-room protocol reconstruction on a proprietary desktop binary using open-source REA. Please provide: 1) [Reverse Engineering Persona System Prompt]: System prompt for Claude Code mandating rigorous cross-reference audits and C pseudo-code verification without assuming memory layouts; 2) [Protocol & Crypto Tracing Prompt Workflow]: Step-by-step instructions directing REA to find crypto constants (AES S-Box), hook network socket handlers, and draft the packet header schema; 3) [Clean-Room Validation Script]: A Node.js socket script constructing sample packets according to the recovered protocol specifications to verify round-trip fidelity.