Gregory Kurtzer Builds New OS Kernel Ginux with AI in 11 Days
The creator of CentOS and Rocky Linux introduced Ginux, an experimental Rust-based kernel that can already run some Linux programs without the Linux kernel.
Gregory Kurtzer, the creator of CentOS and Rocky Linux, developed a new operating system kernel with the help of AI in just 11 days.
The project is called Ginux. It already allows some Linux programs to run without relying on the Linux kernel itself.
Kurtzer defined the system architecture and guided development, while Codex wrote and verified about 139,000 lines of code.
Ginux is built primarily in Rust. It has its own memory management mechanisms, task scheduler, and networking subsystem. In a virtual machine, the system already boots Rocky Linux 10 together with systemd.
For now, Ginux remains an experimental project: compatibility is still far from complete, and hardware support is limited. The source code is published under the Apache 2.0 license.
Eleven days were enough to lay the foundation for a new operating system. The next step is making it reliable.
Project code: Ginux.
Why it matters
AnalysisThe project shows how AI coding assistants can compress the timeline for very complex systems work, even if production readiness still requires substantial engineering.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Part II. How to Work with Codex + Optimization/Security/Team
Codex is not just code autocomplete in a chat; it is a full-fledged engineering agent: it reads the repository, plans changes, edits files, runs tests, reviews its own diffs, and c...
Codex for HR Teams — How to Organize Processes with AI
A comprehensive practical guide to systematic HR process automation with OpenAI Codex: recruiting pipelines, onboarding architectures, compliance tracking, dashboards, and database MCP server integration.
cgroups v2 Resource Quotas & OOM Watchdogs
Linux kernel mechanisms (Control Groups v2) for enforcing strict hardware limits on RAM, CPU, disk, and process counts (PIDs) to protect the host from runaway agent cycles.
eBPF Security & Runtime Auditing
A technology for safely executing bytecode directly within the Linux kernel (eBPF / Tetragon / Falco) to intercept dangerous system calls (syscalls), network connections, and file modifications by AI agents.
OpenAI cuts ChatGPT Pro usage limits from 20x to 10x Plus
After October 29, OpenAI will reduce ChatGPT Pro usage limits from 20 times to 10 times the Plus subscription volume while keeping the $200 monthly price unchanged.
Hackers can hijack Codex and Claude Code via malicious files in the Downloads folder
A plain text file in ~/Downloads can trick AI coding agents into changing settings, installing malware, or leaking authorization tokens, according to Forever Security.