REA

REA is a Model Context Protocol service that enables AI agents to analyze native binaries, Electron apps, .NET assemblies, and websites locally.

REA translates agent questions into local analysis tool calls to investigate software, track code, and return evidence. It covers native binaries, EVM bytecode, Linux crashes, firmware, APKs, and websites through static checks and runtime captures. The tool integrates with external engines like Hopper, Ghidra, IDA, Chrome, JADX, adb, and pwntools to extract pseudocode, assembly, references, and unknown items. It is designed for developers who want to understand existing app features and implement similar functionality. All analysis runs locally on the user machine with open-source code under the MIT license.

REA at a glance

Best for: Software engineer
Runs on: Web, macOS, Windows, Linux, CLI, self-hosted, open source
Pricing: Free and open source under the MIT license.
Released: October 2026
Category: AI coding tool
Website: rea.ndjp.net

Key features

Analyze native binaries, Electron apps, .NET assemblies, and websites locally
Return pseudocode, assembly, references, and clear unknown items
Translate agent questions into local analysis tool calls
Support static checks and runtime captures
Integrate with Hopper, Ghidra, IDA, Chrome, JADX, adb, and pwntools
Run setup workflows that back up and update agent configurations
Provide CLI commands for scriptability and regression testing

Use it for

Reconstruct audio panning calculations from binary code
Trace Electron clipboard bridges from renderer to main process
Recover DOS circular bullet calculations from 16-bit games
Explain and implement features found in existing desktop or web apps

Alternatives to REA

REA Prompts — It provides ready-to-use prompts for investigating native binaries, games, and firmware.
Rea Faang — It gives coding agents structured starting points to build complex products.
REA Reconstruction Companion — Turns reverse-engineering evidence into testable requirements and roadmaps.
jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
TRAE — It features an autonomous coding agent that drives the entire development process.
Reticle — Verifies agent code changes by replaying application flows.
Ret — Manage multiple AI coding agents across projects from one unified desktop interface.
Reika — Manages small local models with careful context discipline and loop breakers.
AG-UI — Standardizes agent-user interactions and generative UI for applications.
Melra — Governs AI agent tool calls with local policies, approval gates, and verified receipts.
Kora Doctor — Surfaces waste across tool usage, context growth, and repeated inference without an account.
Context7 — Provides up-to-date documentation for AI agents and code editors.

All REA alternatives