Urgent.News

What's breaking now, across thousands of outlets.

AI

How I Built a Windows Version of Ghostty in 3 Days with AI

Main Text Ghostty is a terminal tool. It was made by Mitchell Hashimoto, the same person who made Vagrant and Terraform. It uses Zig language at its core. On Mac, it uses Swift. On Linux, it uses GTK. But there is no Windows version. I made a copy (forked it), and three days later, the Windows version was running. The first change (commit) was on September 1st at 2:30 AM. I released the first…

Mitchell Hashimoto, known for creating Vagrant and Terraform, developed a terminal tool called Ghostty using the Zig programming language. While Ghostty works on Mac using Swift and Linux using GTK, there was no Windows version available. The reporter decided to fork the project and created a Windows version in just three days with the help of AI.

The first commit was made on September 1st at 2:30 AM, and the first version was released on September 4th. The Windows portion of the code consists of 45 files and 48,000 lines of Rust.

The reporter used Claude, an AI, to act as an AI CLI manager, automating coding tasks and managing the development process. They set three rules for the AI: workers could not modify Git, two workers could not build the code simultaneously, and the AI should not interact with processes it did not initiate. The reporter chose Rust for the outside layer of the code because it seamlessly integrated with Windows' COM typing system, unlike Zig.

This decision allowed the reporter to modify only about 20 lines of Zig code while keeping the typing system in Rust.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

I Compared 5 LLM Gateway Tools for Real-World Production Use

When an LLM application starts handling real users, calling a model API is usually easy. The problems show up around it. One provider hits a rate limit, another slows down, an endpoint goes down…

  • LiteLLM offers provider abstraction for seamless integration with multiple LLM providers.
  • Kong AI Gateway provides routing and load balancing capabilities for efficient traffic management.
  • Apache APISIX enables reliability through built-in fallbacks and observability features.

More from Wednesday 23 September →