Search results

A Windows lab that pins tool versions, runs health checks and seeds small challenges so you can measure what REA and Ghidra actually give an agent.

A multilingual, daily-updated ranking of cases built with REA.

A Rust and Bevy clean-room port that loads assets from your own Steam install.

A Claude Code mod that keeps a casebook of the evidence REA returns and requires every finding to cite a real evidence id, with Markdown export.

A local MCP server and CLI with pageable evidence, written as an independent Python take on the same idea.

Follows the six-digit code calculation of the open-source Aegis authenticator through its released Android APK, and uses a demo clock to show why the code changes every 30 seconds.

Follow-along exercises from a Korean video: build your own small Electron app and C program, then analyse them with REA, Ghidra and Claude Code.

An experiment that extends REA's idea past the binary: recover behaviour from x86, then express it as VHDL and verify it formally; derived from the upstream project and licensed accordingly.

An agent analysed only the shipped Windows binary of an open-source puzzle game, wrote its findings, froze them, rebuilt the game as a web page and was graded against the real source (52 of 54 claims correct).

A hands-on teaching playbook using a minimal Electron target: extract evidence with file and line references, probe the MCP server and recreate the feature.

A dependency-free static analyser for binaries, apps and web bundles with a compact MCP server, CLI and web UI.

An essay on rebuilding three Touhou games with agents: what verification looks like, where agents help, and how knowledge carries from one project to the next.