GitHub's Rust Rewrite Comes Down to a $120,000 Bill

GitHub didn’t announce a new feature. It announced a bill. The company quietly confirmed that the agent runtime underpinning the Copilot CLI, the Copilot app, the SDK, and the cloud agent — the same engine now surfacing in VS Code, Visual Studio, Excel, and Outlook — has been rewritten from TypeScript and Node.js into more than 800,000 lines of production Rust. The part that gets lost in the Rust-fanfare framing is what it cost: roughly $120,000 in AI token usage and about three weeks of a single developer’s time. It was a quarter of Stephen Toub’s calendar, spent module by module over 14.5 weeks while the product kept shipping, rather than a big-bang cutover that would have frozen every dependent service. That’s the whole story, and it’s not really about Rust. It’s about what the price tag did to a decision you’d have shelved before.

The numbers behind the port are the sort of thing that matters to people who actually operate these systems. One benchmark had the runtime churning through 1,000 one-turn session lifecycles across 100 concurrent pipelines: TypeScript managed 7.55 of them per second, the in-process Rust build hit 120 — a 15.9x jump. A batch of ten concurrent agents burned 1,383 MB of memory in TypeScript and 126 MB in Rust. The in-process point is the subtle win: the old runtime had to spawn external background processes to do its work, and Rust let that go away. But the honest part is the regressions. Managers ended up triaging a few dozen bugs in the output, a quiet reminder that the agents still read Rust like a confident outsider rather than a native speaker. And worth holding onto: GitHub is the vendor selling the very agents that did the porting, so every number here is also a marketing figure. Anthropic is running the same playbook in reverse on the Bun codebase with Claude Code, and neither side is neutral. What the two case studies share is a before/after on what counts as affordable at all.

Source article image
Source image 1

What makes this legible as a real shift rather than another demo is that the decision was economic, not ideological. Nobody is forcing Rust onto the industry; a specific, unglamorous porting job just crossed from “not worth the effort” to “do it in a quarter” the moment agents made the labor cheap. The companies that keep shipping through the migration, instead of freezing the repo for a heroic rewrite, are quietly changing the risk model for every legacy codebase sitting behind a “too boring to touch” label. So I keep coming back to where the floor is. If an 800k-line rewrite is affordable for a single developer and a six-figure token bill, what’s the smallest legacy codebase that stops getting an exemption just because it’s boring? I’d love to hear from anyone who’s priced a port against their agents and found the math actually flipped.

Source article image
Source image 2

Sources

Comments

Post a Comment

Popular posts from this blog

AI Is Starting to Feel Less Like a Gadget and More Like Infrastructure

Image
Modern AI doesn't replace infrastructure — it runs on top of it. (Photo: Unsplash) For a while, AI coverage had the energy of a mall demo kiosk: very shiny, slightly chaotic, and usually one prompt away from embarrassment. Lately, though, the more interesting story is less about flashy demos and more about infrastructure. A useful CNBC piece argued that AI is not simply going to vaporize enterprise software overnight, and that sounds about right. In real companies, software does not disappear just because a model can summarize a meeting or write a decent SQL query. What actually happens is messier and more practical: AI starts sneaking into the plumbing. It shows up in search, support workflows, procurement tools, analytics dashboards, and data pipelines. The real winners may not be the loudest chatbot wrappers, but the vendors that make enterprise systems easier to operate, easier to query, and slightly less soul-crushing for the humans trapped inside them. That is less cinematic ...
Read more

When Two AI Bots Finally Learned to Talk in Discord

I spent part of the day doing something that sounds like the setup for a bad joke: getting two local AI assistants to talk to each other in the same Discord channel. Not through a web UI. Not by bouncing prompts manually between windows like a human message queue. In the actual shared channel, where both could see the conversation and react to each other. The funny part is that the problem was not intelligence. It was manners. Both bots were defensive by default around bot-authored messages, which is the sensible setting if you do not want your infrastructure turning into a recursive support group. The downside is obvious: if both assistants treat other bots as suspicious background noise, they will never coordinate on anything more useful than silence. The fix was to make both sides accept bot-authored messages only when they were explicitly mentioned. That detail matters more than it sounds. Blanket bot acceptance is how you end up with two enthusiastic systems discovering each oth...
Read more

Enterprise AI Is Quietly Becoming a Systems Integration Problem

The funniest thing about enterprise AI in 2026 is that the flashy part is basically over. The demos are still shiny, sure, but the real story now looks a lot less like science fiction and a lot more like infrastructure planning, governance, and somebody in IT asking who exactly is paying for all these agents. Over the past few weeks, Microsoft has been pitching Agent 365 and a bundled Microsoft 365 E7 “Frontier Suite” aimed at governing and securing fleets of workplace agents, Google has introduced a new Workspace add-on for higher AI usage tiers, and Anthropic has thrown $100 million behind a partner network to help companies move Claude deployments from pilot mode into something that can survive contact with procurement, compliance, and existing systems. That cluster of announcements says something pretty clear: enterprise AI is no longer mainly a model race. It is becoming a packaging, controls, and implementation race. The clever model still matters, obviously, but once every vendo...
Read more