cd /news/artificial-intelligence/streets-of-rage-streets-of-rage-ruin… · home › topics › artificial-intelligence › article
[ARTICLE · art-160765] src=reversedwithai.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

Streets of Rage: Streets of Rage: RuiNelson combines LLM analysis and RageDecompiler to recompile 68000 logic into C++

Developer RuiNelson built a custom tool called RageDecompiler that transpiles Motorola 68000 assembly from the SEGA Mega Drive version of Streets of Rage into C++ for a native PC build, using Claude, ChatGPT and Grok 4.5 to assist with code analysis and manual reimplementation of specific routines. The hybrid project runs translated game logic natively while hardware-specific video and audio functions still rely on an emulated Mega Drive environment powered by SDL3, and it includes a symbolic AI player written in Python that connects to the running game process to observe state and issue controller inputs without neural networks. The work in progress requires a user-supplied Rev. A ROM (CRC32 4052E845) to build via the Streets of Rage Builder.

by read1 min views1 publishedOct 30, 2026
Streets of Rage: Streets of Rage: RuiNelson combines LLM analysis and RageDecompiler to recompile 68000 logic into C++
Image: Reversedwithai (auto-discovered)

Evidence at a glance #

source evidence…

What was done #

RuiNelson uses a custom tool, RageDecompiler, to translate Motorola 68000 assembly into C++ for a native PC build of Streets of Rage. The project employs LLMs for code analysis and includes a symbolic AI player that interacts with the game via a remote-access library.

The Streets of Rage project is a reverse-engineering and recompilation effort targeting the SEGA Mega Drive game. The developer, RuiNelson, created a tool named RageDecompiler to disassemble the ROM and transpile Motorola 68000 assembly routines into C++. The project uses a hybrid approach where game logic is translated to native C++, while hardware-specific functions like video and audio currently rely on an emulated Mega Drive environment powered by SDL3. The author credits Claude, ChatGPT, and Grok 4.5 for assisting with code analysis and manual reimplementation of specific routines. A symbolic AI player, implemented in Python, connects to the running game process to observe state and issue controller inputs. This AI does not use neural networks; it relies on the disassembly and analysis data to navigate stages and fight enemies. The project is a work in progress and requires a user-supplied Rev. A ROM (CRC32 4052E845) to build. Development is documented at https://raw.githubusercontent.com/ruinelson/streetsofrageproject/HEAD/README.md.

From the source #

Reproduce it #

Use the Streets of Rage Builder to install tools, provide a Rev. A ROM, and build the executable. The builder automates the process of cloning the repository, verifying the ROM, rendering the soundtrack, and compiling the game.

Community #

Ask a question, share what worked, or follow the next milestone.

Your library

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @ruinelson 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/streets-of-rage-stre…] indexed:0 read:1min 2026-10-30 · —