Overview
REA is a developer tool that integrates reverse engineering capabilities into coding agents for software developers, reverse engineers, security researchers, and technical teams that need to analyze legacy systems. It helps users understand how a program or webpage works internally, reducing the time it takes to manually read compilations, trace function calls, and analyze running behavior. REA can connect to MCP-enabled coding agents such as Codex, Claude Code, Cursor, Gemini CLI, etc., or run directly in the terminal. After the user provides a local application, Electron project, native binary, or browser page, and asks specific questions, the REA returns code structure, call relationships, instructions, requests, and run results, which are then interpreted by the Agent to explain behavior, validate rules, or assist in rebuilding functionality. Its analysis is mainly done on-premises, and there is no need to upload the application as a whole to the cloud first. Core function encoding Agent access: Connect REA to MCP-enabled Agents such as Codex, Claude Code, Cursor, etc. through npx rea-agents @ latest setup, so that Agents can obtain reverse analysis tools.
Connected profiles
More Coding assistants products
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
REA 是一个将逆向工程能力接入编码 Agent 的开发者工具，主要面向软件开发者、逆向工程师、安全研究人员和需要分析旧系统的技术团队。它帮助用户理解一个程序或网页内部是如何工作的，减少手动阅读汇编、追踪函数调用和分析运行行为的时间。REA 可以连接 Codex、Claude Code、Cursor、Gemini CLI 等支持 MCP 的编码 Agent，也可以直接在终端运行。用户提供本地应用、Electron 项目、原生二进制或浏览器页面，并提出具体问题后，REA 会返回代码结构、调用关系、指令、请求和运行结果，再由 Agent 解释行为、验证规则或协助重建功能。它的分析主要在本机进行，不需要先将应用整体上传到云端。核心功能编码 Agent 接入：通过 npx rea-agents@latest setup 将 REA 连接到支持 MCP 的 Codex、Claude Code、Cursor 等 Agent，让 Agent 获得逆向分析工具。