Open-source REA hooks reverse engineering into Claude Code, Codex and Cursor via MCP
dotey · x · 2026-10-10
REA (Reverse Engineer Anything) is an open-source MCP service that plugs reverse-engineering capabilities into AI coding agents like Claude Code, Codex, Cursor, Gemini CLI and Grok Build, installable with npx rea-agents setup.
What it can analyze:
- Native binaries, via Hopper, Ghidra or IDA disassembly into pseudocode
- Electron apps by unpacking ASAR archives (e.g. Notion)
- Also .NET, Android APKs, firmware, websites, packet captures, Ethereum contract bytecode, and runtime tracing on Linux/macOS
Demo cases: recovering DX-Ball's stereo-panning function as C code matching the original in 3,205 tests; tracing Notion's copy-paste path through preload scripts and IPC; extracting the bullet-ring angle algorithm from TH04 on PC-98's 16-bit instructions.
Analysis runs locally without uploading targets, though results go to the agent's model provider.
More from coding & agent
- Andrew Ng releases 1-hour course on building agentic knowledge graphs from scratch — nikola_mr64990 · 2026-10-10
- Mnemos: an engram-inspired memory architecture doubles short-term recall vs Claude's native memory — RileyRalmuto · 2026-10-10
- LLM reliability #6-7: guardrails, fallbacks, and production monitoring — goyalshaliniuk · 2026-10-10
- LLM reliability #4-5: abstaining gracefully and controlling context quality — goyalshaliniuk · 2026-10-10
- LLM reliability #3-4: strong eval suites and graceful abstention — goyalshaliniuk · 2026-10-10
- 7 ways to improve LLM reliability, from RAG grounding to production monitoring — goyalshaliniuk · 2026-10-10