Radar / AI coding tools / REA
REA: reverse engineer anything with agents
An MIT-licensed MCP server and CLI that lets coding agents drive real reverse-engineering tools — Ghidra, IDA, Hopper and built-in inspectors — and return evidence-backed findings on any app or binary.
Why it matters
The most-starred repo of the year: 470k stars for giving agents a stable, evidence-first way to take software apart instead of guessing from screenshots.
What you could build with it
A security team could point an agent at a suspicious binary and have it produce an evidence-backed report on what the sample does — which APIs it calls, what it touches on disk — before anyone runs it in a sandbox, turning a day of manual triage into a repeatable check.
Does it hold up?
People are already using it to take apart real apps — one walkthrough traces how Obsidian updates itself without its installer — and setup is a single npx command; the honest limits are that native binaries still need an installed engine (Hopper, IDA or Ghidra) and it returns a reconstruction, never the original source.
Built with REA
- The REA GitHub repo (morluto/rea) explainedmedium · A tour of what the repo installs, what it can analyze, which download sources are official, and the one kind of code it still cannot open.
- How to reverse engineer anythingarticle · Walks through taking apart how Obsidian updates itself without ever running its installer, using REA's evidence records.
- REA Hits 420k Stars: Local MCP for Agents to Disassemble Binaries with Evidencedev.to · How the local MCP lets agents disassemble binaries with an evidence contract instead of unstructured tool output.
Learn more
First spotted on github: source.
More AI coding tools
Chrome DevTools MCP: give your coding agent a real browserOfficial MCP server from the Chrome team that lets coding agents drive a live Chrome — console, network, traces…coding · JEV 0.82Orca: the agent development environment for running coding-agent fleetsStably AI's open-source desktop app for running many CLI coding agents side by side — Claude Code, Codex, Cursor and…coding · JEV 0.78Open Code Review: Alibaba's hybrid AI code reviewer, now past 50,000 starsAlibaba's open-source code review CLI (Apache 2.0) pairs deterministic rules with an LLM agent to review git diffs…coding · JEV 0.77Cursor Plugins: an official plugin spec and marketplace for AI coding agentsCursor's official plugin specification and catalogue: plugins bundle skills, subagents, MCP servers, hooks and rules…coding · JEV 0.76Ponytail: the 'laziest senior dev' skill for coding agentsA single SKILL.md that makes coding agents check whether code needs to exist, reuse what the codebase or platform…coding · JEV 0.74Caveman: the viral agent skill that makes coding agents talk in telegraphic fragmentsAn agent skill plus local proxy that forces coding agents to answer in short, plain fragments and shrinks the context…coding · JEV 0.74
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.