The rewrite that wasn't affordable before agents happened. github ported the copilot runtime from…
the rewrite that wasn't affordable before agents happened. github ported the copilot runtime from ~430k lines of typescript to 832k lines of rust in 14.5 weeks, agents writing most of it across 128 prs.
the thing that blocked rewrites was never skill, it was cost.
Context
GitHub's blog post of 16 September 2026 by Stephen Toub says a rewrite this size was not affordable before agents. By 21 August the Copilot runtime was 100 percent production Rust: 832,378 lines of production Rust plus 468,689 lines of Rust unit tests, with AI agents writing most of the code across 128 pull requests. The timeline runs from 12 May to 21 August, and the author estimates about 430,000 lines of production TypeScript passed through the port, against an early-May plan of about 130,000. Of 2,639 human messages, 31.0 percent concerned review, testing and CI.
The 832k is production lines only; the test lines are separate. The 430k is the author's estimate of TypeScript that passed through the port, not the size of the starting codebase, so from 430k to 832k is the note's reading. 14.5 weeks is not a phrase in the post; 12 May to 21 August is 101 days, about 14.4 weeks. The post names other reasons for Rust (embedding through a C ABI, low startup, predictable resources), so cost was not the only factor. A roughly 120,000 dollar cost from The Register was seen as a snippet and is not repeated here as verified. That the blocker was cost and not skill is the author's thesis, with the post's own line that this was not affordable before agents. One migration, GitHub's own.
Related work
- Earlier note on the same migration ↗Same post.
Watch next
- GitHub's cost and regression figures, and results from other codebases.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 04:18 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →