TopicTrending open-source AI on GitHub
REA Review: Letting Agents Reverse-Engineer Anything, 100K Stars in a Week
Open-source REA gained 100K stars in a week: an MCP server that lets coding agents like Claude Code, Codex and Cursor call decompilers such as Ghidra, IDA and Hopper directly — reading software without its source.

Scorecard
8.6/ 10
HIMIAO Horizon score
Infrastructure-grade tooling: testing proves the static analysis works; deep native analysis depends on backend setup.
Pros
Broad MCP ecosystem support
Static JS analysis verified fast and solid by independent testing
MIT-licensed with fast iteration
Cons
Independent testing found misses
Native analysis needs paid or heavy backends
Legal boundaries are the user's own responsibility — analyze only software you are allowed to
Best for
Developers who need to understand closed-source apps, build compatible implementations or play CTFs
01What happened
REA (Reverse Engineer Anything, morluto/rea, MIT-licensed) began in April 2026 as betterBinaryMCP. Version 4.1.0 on October 6 added JADX Android APK analysis, Binwalk/Unblob firmware analysis and read-only IDA access, followed by rapid 5.0.0 (October 7) and 6.0.0 (October 8) releases. Stars climbed from under 10K on October 6 to over 38K by October 9 and over 100K by October 12 (one report cites 115K), topping GitHub's daily trending with 25K+ new stars in a single day. How it works: an agent calls REA over MCP, and REA routes the question to a local decompiler or disassembler (Ghidra, Hopper, IDA, JADX, firmware tools), returning pseudocode, assembly, strings and “evidence and limitations.” Installation: npx rea-agents setup.
02Testing and results
The basis is a published independent hands-on test (dev.to, October 12, 2026): a Debian 13 box with 8 vCPUs, no GPU and no cloud API keys; REA was driven through its own CLI and a hand-written MCP script (testing the tools, not an agent's judgment); targets were a 100MB Electron app (459 files) and a self-built 5-file toy app with known answers. Results: static JS analysis was fast and solid, but missed two preload files visible via grep, and the tooling places a heavy call burden on agents. Vendor case study: one DX-Ball function rebuilt in C passes 3,205 test cases against the original x86 code (vendor data). For context: SRE-Bench shows the best agent fully solving 31.5% of realistic test binaries.
03Key facts
- Works with: MCP agents including Claude Code, Codex, Cursor and Gemini CLI.
- Backends: Ghidra, JADX and firmware tools are free; Hopper is paid; IDA needs the Pro edition; Ghidra and IDA paths are read-only analysis.
- Project health: CI, a security policy, a docs site and a Discord community; the README ships in Chinese, Japanese, Korean and Arabic.
- Disputes: Activision reportedly pulled AI-decompiled game footage, and Bethesda issued a cease-and-desist against an AI-generated browser game.
Why it matters
100K stars in a week shows real developer demand for agents that can read closed-source software — REA turned decompilation into an MCP tool agents can call.
From HIMIAO Horizon · himiao.ai
Comments
Related
- Oct 11context-mode Hits GitHub Trending: Tool Output, Sandboxed First
- Oct 8REA Tops GitHub Trending: Let AI Agents Reverse-Engineer Anything, Down to the Binary
- Oct 12India's HCLTech Signs Pact With Anthropic, Sets Up Dedicated Unit for Enterprise Agents
- Oct 12TomTom and DeepRoute.ai Sign Deal on AI Automated Driving, With an Open-Road Demo at the Paris Motor Show
- Oct 12colibri Hits GitHub Trending: Pure-C Engine Runs a 744B Model on Ordinary PCs
Today
Oct 14 Wednesday- BriefGoogle Opens Gemini 4 Argon to Developers and Businesses Worldwide
20 stories · Oct 13
- Quiz
- Call
Latest news
All →- Oct 13Google Opens Gemini 4 Argon to Developers and Businesses Worldwide
- Oct 13Suno Speech vs ElevenLabs Eleven v4: One-Pass Soundtrack vs Expression Control
- Oct 13PageIndex vs Graphify: Structured Retrieval Tools Compared
- Oct 13Claude Haiku 5.5 vs GPT-6 Instant: Lightweight Speed Models Compared
- Oct 13Drex 1.5 vs Decision-1: The Models That Score, Not Write
- Oct 13Muse Wonder vs GPT-6: Two Flagships Meet in One Week
™