The github copilot runtime now runs on 800,000 lines of rust, ported with the agent it hosts.…
the github copilot runtime now runs on 800,000 lines of rust, ported with the agent it hosts. microsoft's september 16 post credits the rewrite to copilot itself — work that size was never affordable before agents.
the agent just rewrote the platform it runs on.
Context
GitHub's blog of 16 September 2026, Migrating the GitHub Copilot runtime to Rust using Copilot, says the runtime was rewritten into more than 800,000 lines of production Rust, that AI agents wrote most of the code across 128 pull requests, primarily by a single developer in a few months, and that a rewrite this size was not affordable before agents. It gives about 830,000 production Rust lines at the end, about 469,000 test lines and about 430,000 TypeScript lines passed through the port, and says it is not a claim that every large TypeScript program should become Rust.
The size, 128 pull requests and timing are first-party. The post is from GitHub, which is Microsoft-owned; the note says Microsoft's post. Credits the rewrite to Copilot itself overstates: AI agents wrote most of the code with a human developer leading. The three line counts are different measures. The agent just rewrote the platform it runs on is the author's take.
The post's own sentence says that by 21 August the runtime was 100 percent production Rust, with 832,378 lines of production Rust and 468,689 lines of Rust unit tests. So 832,000 is a rounding of the production count as of that date, excluding tests; the post also says more than 800,000 in prose and approximately 830,000 in a chart caption, and does not state the count on the post date.
Watch next
- Independent reproduction of the cost and regression claims.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 21:41 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 →