DigestAI news desk

Cut through the AI noise.

Agents & Tools4 min read

Open-source REA hits 100,000 GitHub stars as AI agents decompile software

The open‑source toolkit REA (Reverse Engineer Anything) surged from under 10,000 GitHub stars on October 6 to more than 100,000 by October 12, with a single day spike of over 30,000 stars on October 11. REA links AI coding assistants such as Anthropic’s Claude Code and OpenAI’s Codex to reverse‑engineering suites like Ghidra via the Model Context Protocol, letting users point an agent at a…

1 source

Key points

  • REA grew from under 10,000 to over 100,000 GitHub stars between October 6 and October 12, adding more than 30,000 on October 11.
  • The toolkit connects Claude Code or OpenAI’s Codex to Ghidra through Anthropic’s Model Context Protocol.
  • Brandon Thomas used Claude Opus 5.5 to create free ArtCraft apps, citing Adobe’s $150 million settlement as a trigger.

Developers have already used the pipeline to create AI‑decompiled game mashups—Spider‑Man in Arkham City, an unofficial PC port of Fable 2, and a GTA V build for iOS. Brandon Thomas leveraged Claude Opus 5.5 to launch ArtCraft, a free Rust‑built suite that mimics Adobe Photoshop, Illustrator, Premiere and Lightroom, citing Adobe’s $150 million settlement over subscription fees as motivation. While ArtCraft is an early‑alpha clean‑room rebuild, the broader trend raises concerns about software piracy, copy‑protection erosion, and legal push‑backs from studios such as Activision and Bethesda.

Model page: Claude Opus 5.5 →

Full story from decrypt.co · by Decrypt / Jose Antonio Lanz · via Search: GitHubOpen source ↗

From GTA V on iPhone to Free Photoshop: This AI Tool Is Upending Software

decrypt.co · 12 October 2026

Loading the full article…

This text was published by decrypt.co and written by Decrypt / Jose Antonio Lanz. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Agents & Tools

All →

Related stories