Urgent.News

What's breaking now, across thousands of outlets.

AI

GitHub and Anthropic used their own agents for major Rust rewrites — with very different playbooks

Rust is seemingly the language of the moment, with open-source projects and companies forming an orderly queue to move core The post GitHub and Anthropic used their own agents for major Rust rewrites — with very different playbooks appeared first on The New Stack .

GitHub and Anthropic used their own agents for major Rust rewrites — with very different playbooks

GitHub and Anthropic have each employed their own AI agents to conduct major Rust rewrites, each employing a distinct approach. Microsoft subsidiary GitHub has reworked the GitHub Copilot agent runtime, which was originally written in TypeScript using Node.js and V8, into over 800,000 lines of production Rust. The migration was carried out using GitHub Copilot agents, with 128 pull requests merged incrementally, enabling the team to fix regressions while continuing to expand the runtime's functionality.

Microsoft engineer Stephen Toub stated that the project, which would have taken a team of developers a year or two, was completed by a single developer in just a few months.

On the other hand, Anthropic's acquired runtime Bun, previously written in Zig, has transitioned to Rust by using a pre-release Claude model to assist with the rewrite. Founder Jarred Sumner employed Claude to translate and verify distinct parts of the Bun codebase concurrently, while he oversaw the work and intervened as needed.

Within eleven days, the Rust version was successfully passing Bun's existing tests on all supported platforms. The Rust language provides enhanced memory safety protections, but switching languages presented its own challenges due to the size of the codebase. Sumner reasoned that a traditional rewrite would require a small engineering team for about a year, making it impractical.

Consequently, he utilized multiple Claude Code agents to perform the translation and verification simultaneously, which streamlined the process and reduced the time required.

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

This story

This is one outlet's version. Read the fullest account.

Read the original at thenewstack.io →

More in AI

More from Thursday 17 September →