morluto/rea
Reverse engineer anything with agents, from app behavior down to native binaries.
What it solves
REA helps you understand how software features work by inspecting applications without needing their source code. It allows you to analyze binaries, websites, and mobile apps to see how they are built, enabling you to replicate features or understand complex behaviors down to the binary level.
How it works
REA acts as a bridge between your AI agent and the target software. By connecting to your agent via the Model Context Protocol (MCP), it provides tools to inspect native binaries, JavaScript, .NET assemblies, and more. You ask your agent a question about a feature, and REA performs the technical investigation, returning findings and evidence that the agent uses to explain the code or help you write a similar implementation.
Who it’s for
This tool is for developers and researchers who want to use AI agents to automate the process of reverse engineering, feature analysis, or software auditing across a wide variety of platforms and file types.
Highlights
- Supports a vast range of targets including native binaries, Electron apps, Android APKs, .NET assemblies, and GPU code objects.
- Integrates with popular AI agents like Claude Code, Cursor, and Gemini CLI.
- Provides evidence-based results, including pseudocode, assembly, symbols, and dependency maps.
- Runs analysis locally to maintain control over your data and investigation process.
- Works with existing industry tools like Ghidra, Hopper, IDA, and JADX for deep binary analysis.
Related
- Project
NabilRFG12/Reverse-Engineer-anythingREA (Reverse Engineer Anything) is a Node.js platform that lets AI agents automatically analyze binaries, JavaScript/Electron apps, .NET assemblies, Android APKs, firmware, websites, and more. It runs traditional reverse‑engineering tools (Hopper, Ghidra, IDA, pwntools, JADX, Binwalk, browsers) behind a local MCP server, returns structured evidence (pseudocode, module graphs, network data), and enables the LLM to explain or re‑implement the observed behavior. Setup is done via `npx rea‑agents setup`, and the same capabilities are available through a CLI. The project targets lawful reverse‑engineering research and integrates with agents such as Claude, Gemini, and Grok.
- Dispatch
- Project
bbylw/rea-cnREA is a Node‑JS platform that connects LLM agents to reverse‑engineering tools (Hopper, Ghidra, IDA, etc.) and static analysis utilities for binaries, JavaScript/Electron, .NET, Android, firmware, web captures and more. It runs a local MCP service, registers a skill with supported agents, and returns concrete evidence (pseudo‑code, assembly, module graphs, screenshots) that the AI can use to explain or re‑implement a target feature. Install via `npx rea‑agents setup`, then ask questions or use the CLI (`rea …`).
- Project
AIshihzong/awesome-reverse-engineer-anythingA curated list of projects where AI agents reverse-engineer and rebuild closed software, documenting which cases genuinely used the REA tool versus other approaches, and including controlled tests on whether REA actually helps.
- Project
JoasASantos/REA-PromptsA community‑curated library of structured prompts for the REA AI reverse‑engineering agent, covering binaries, firmware, Android, games, kernels, and security research. Prompts enforce evidence‑backed, single‑feature investigations and guide users from installation through clean‑room cloning and vulnerability analysis.