When the source code finally surfaced (primarily for OS/2 1.2 and 1.3 from the late 1980s, with fragments of 2.0), it told a story of engineering brilliance hamstrung by corporate politics.
Look at the date stamps. Read the comments. See the FIXME notes that were never fixed. Notice the sheer craft—the hand-tuned assembly loops, the clever data structures, the desperate hope that this, this would be the OS that killed the Mac and buried Unix.
That is, until recently, when the unthinkable happened: os 2 source code
There is nothing in the OS/2 source that is technically inferior to Windows 3.1. In fact, OS/2’s crash recovery and memory protection were objectively superior. But Microsoft had better developer tools, cheaper licenses, and a ruthless focus on the desktop. IBM had mainframe culture. The source code proves it: OS/2 is a server in desktop clothing. Windows is a toy that grew up. The Ethical Gray Area Let’s address the elephant in the room: This source code is proprietary. It belongs to IBM (and maybe some bits still owned by Microsoft). Leaking it was almost certainly illegal. However, for a dead platform—one that hasn’t been commercially relevant in 25 years—the archival argument is strong.
For historians, developers, and retro-computing enthusiasts, this wasn't just a zip file of C and assembly files. It was the discovery of a lost civilization. Let’s dive into why the OS/2 source code matters, what it contains, and what it tells us about the road not taken in personal computing. To understand the value of the source code, you have to understand the pain of the OS/2 user. By 1991, the relationship between IBM and Microsoft had curdled into open warfare. Microsoft was secretly pouring its best talent into Windows 3.0, while IBM kept paying for OS/2 1.x development. When the source code finally surfaced (primarily for OS/2 1
It wasn’t. But for a few glorious years, OS/2 was the best operating system nobody used. And now, thanks to a leak, we can finally read its diary. For educational purposes only. If you’re a student of operating systems, hunt down the OS/2 1.3 kernel leak. Compile it (good luck finding a 16-bit IBM C compiler). Run it in an emulator. And when it boots—when that blue screen with the white text appears—raise a glass to the engineers who built a cathedral in the age of bazaars.
One comment in pmdrv.asm reads: "REV 1.34: Fixed race condition. Again. If Bill G. actually shipped this, users would hang daily. Good thing we have six more months of testing." Another, in the memory manager: "This entire module is a hack to support the 286's stupid segmented architecture. When the 386 ships, rewrite from scratch." (Spoiler: They never did, fully. OS/2 2.0 still carried 286 compatibility baggage.) And the most haunting comment, found in the boot loader: "If Microsoft ships Windows 3.0 with VxD support before we ship OS/2 1.3, we are dead. -- Dave, 10/12/1989" Dave was right. Why should a modern developer—someone building React apps or Kubernetes clusters—care about thirty-year-old assembly code? See the FIXME notes that were never fixed
It was the "Operating System of the Future." At least, that’s what the billboards promised in 1987. A joint venture between IBM and Microsoft, OS/2 was supposed to dethrone DOS, tame the 286’s protected mode, and eventually run on everything from point-of-sale terminals to massive IBM mainframes.