---
title: "Bun 项目从 Zig 重写为 Rust：借助 AI 代理的 11 天工程奇迹"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Jul/8/rewriting-bun-in-rust/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_50ca3cf531e4b912fdd2027a"
published: "2026-07-08T23:57:21.000Z"
score: 78
channel: "ai"
tags: ["Agentic Engineering","AI辅助编程","Bun","Claude","Rust","Zig"]
---

# Bun 项目从 Zig 重写为 Rust：借助 AI 代理的 11 天工程奇迹

## AI 点评

> 这篇博客是AI代理工程能力的里程碑式展示。它不仅打破了“不要从头重写”的经典教条，还公开了惊人的成本数据和实操细节。对于任何在大型代码库上尝试AI辅助重构的团队来说，都是必读材料。Jarred对Zig的诚实评价也值得学习。

## 速览

Bun 的创建者 Jarred Sumner 发布博客，详细描述了他如何利用 AI 编码代理（基于 Anthropic 的 Mythos/Fable 模型）在短短 11 天内将整个 Bun 运行时从 Zig 重写为 Rust。重写过程中，AI 生成了超过 100 万行代码，消耗了约 165,000 美元的 token 费用，并依赖 TypeScript 编写的测试套件作为符合性标准。通过对抗性代码审查和流程修复，团队成功合并了这次大规模重写。新版本已在 Claude Code 中上线，启动速度提升 10%。这一案例展示了 AI 代理在大型软件工程中的潜力。

## 关键点

- Bun 的创建者 Jarred Sumner 使用 AI 编码代理在 11 天内将 Bun 从 Zig 重写为 Rust，消耗约 16.5 万美元 token 费用。
- 重写过程依赖 TypeScript 测试套件作为符合性标准，通过对抗性审查和流程修复确保代码质量。
- 重写原因：Zig 的手动内存管理导致大量 use-after-free、double-free 等 bug；Rust 的安全保证能消除此类问题。
- 新版本已在 Claude Code 中上线，启动速度提升 10%，用户几乎未察觉变化。

## 全文

Rewriting Bun in Rust Jarred Sumner has been promising this blog post (since May 9th) about his Zig to Rust rewrite of Bun for significantly longer than it took him to finish the rewrite. Honestly, it was worth the wait. This is a detailed description of an extremely sophisticated piece of agentic engineering, featuring dynamic workflows, trial runs, adversarial review and all sorts of other interesting tricks. Jarred spends the first half of the post praising Zig for getting Bun this far. Then we get to a core idea in the piece, emphasis mine: Our bugfix list felt bad and I was tired of going to sleep worrying about crashes in Bun. I don't blame Zig for that - other users of Zig don't have the bugs we had, and mixing GC with manually-managed memory is an uncommon enough thing for software to need that no language really designs for it. We wouldn't have gotten this far if not for Zig, and I'll always be grateful. Until very recently, programming language choice was a one-way decision for a project like Bun. Everyone knows you should never stop the world and rewrite a large piece of software from the ground up. Joel Spolsky highlighted that in Things You Should Never Do, Part I back in April 2000! Coding agents powered by today's frontier models change that equation. Why pick Rust? It all came down to those challenges with memory management: A large percentage of bugs from that list are use-after-free, double-free, and "forgot to free" in an error path. In safe Rust, these are compiler errors and RAII-like automatic cleanup with Drop. A crucial enabling factor for the rewrite was that the Bun test suite was written in TypeScript, which meant it could act as a conformance suite. This allowed an agent harness to automate much of the initial port from Bun to Rust, initially as an experiment to try out an earlier version of the model we now have access to as Mythos/Fable. At first, I didn't expect it to work. A few days in, a high % of the test suite started passing and I saw how much the new Rust code matched up with the original Zig codebase. My opinion went from "this is worth trying" to "I'm going to merge this". [...] For most of those 11 days (and after), I monitored workflows - manually reading the outputs to check for issues and bugs, and prompting Claude to edit the loop to fix things. How do you review a PR with +1 million lines added? How do you start to build the confidence needed to responsibly merge large quantities of LLM-authored code? A language-independent test suite with a million assertions, adversarial code review and when something does go wrong, fixing the process that generates the code instead of hand-fixing the code. The new implementation of Bun has been live in Claude Code for nearly a month now: Claude Code v2.1.181 (released June 17th) and later use the Rust port of Bun. Startup got 10% faster on Linux but otherwise, barely anyone noticed. Boring is good. A perk of working at Anthropic is that you don't have to pay for your tokens - handy when the estimated cost is $165,000! Pre-merge, this took 5.9 billion uncached input tokens, 690 million output tokens, and 72 billion cached input token reads — around $165,000 at API pricing. This whole thing is a fascinating case study in taking on wildly ambitious projects with the help of coordinated parallel agents. Via Hacker News Tags: ai, rust, zig, generative-ai, llms, ai-assisted-programming, anthropic, bun, conformance-suites, agentic-engineering, claude-mythos-fable

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_50ca3cf531e4b912fdd2027a