ClawDOS: AI coding agent built to run on an IBM PC XT under DOS
Article Content
Browse articles
- •ClawDOS is a hobby project: an AI coding agent that runs on an IBM PC XT (8088, 4.77 MHz, 640K RAM, CGA).
- •The author states the code was written by Claude, with a separate bridge PC handling TLS.
- •The articles report no vulnerability, exploitation, or security incident.
- •No CVEs, indicators of compromise, or detection guidance are provided.
A Hacker News post and a GitHub repository (Ricapar/ClawDOS) describe ClawDOS, an AI coding agent designed to run on an IBM PC XT with an 8088 processor at 4.77 MHz, 640K of RAM and a CGA card. The project was written by Claude, according to the author's note, and was built as a personal experiment in running an AI coding agent under original-hardware constraints. The harness runs on the native DOS hardware and relies on a separate 'bridge' PC to handle TLS, which the author says the 8088 could not manage. The articles describe a hobby project and do not report any vulnerability, attack, or security incident. No CVEs, IOCs, or affected third-party systems are mentioned.
Ask AI about this cluster
Answers cite the sources they use
Updated 6h ago How this analysis works
Timeline
2026-11-21
ClawDOS posted to Hacker News and GitHub
The project was published as an AI coding agent for DOS on IBM PC XT hardware, with the author describing it as built for personal entertainment.
News.YcombinatorMore articles in this cluster (6)
Common questions
Am I affected by this?
No. The articles describe a hobby project for vintage IBM PC hardware and report no vulnerability or security impact.
Is any action required?
No defensive action is indicated, since the articles contain no CVEs, IOCs, or exploitation reports.
Is this a security tool or threat?
Neither. It is an AI coding agent experiment running on DOS hardware, described by its author as personal entertainment.
Continue Reading
Lazarus Group Targets 30 South Korean Servers Using PHP Vulnerabilities North Korea-linked Lazarus Group has targeted 30 servers in South Korea as part of a larger cyber operation involving 581 servers across 10 countries. The attacks exploit two critical remote code execution vulnerabilities in PHP (CVE-2026-109618 and CVE-2026-109619), allowing unauthorized server command execution. The…