Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

A native TypeScript/JavaScript compiler written in Rust. Compiles TypeScript/JavaScript directly to executables using SWC and LLVM.

01Result

PerryTS/perry ↗

PerryTS/perry AI coding statistics: 9.1%

of 8,578 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
9.1% agent · top contributor 85.2%12 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

777
agent commits
7,801
other considered commits
12
agent contributors
85.2%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

776assisted
1autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0296.9%128
2026-0370.2%426
2026-044.5%1031
2026-051.2%2094
2026-0613.9%1391
2026-0710.4%825
2026-080.3%1384
2026-090%1299

Peak month: 96.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7769%
OpenAI CodexOpenAI10%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 9c8cdfc2 on GitHubfix(link,crypto): ELF archive grouping and scrypt cost parameters (from #9Claude Code
  • e8c08aab on GitHubfix(bench): reject implausible wall times; correct polyglot bench.rs setupClaude Code
  • 9d0be5f2 on GitHubtest(link): regression guard for #8907 — full-stdlib links without the httClaude Code
  • 9a9a233c on GitHubfix: address #945 scalar method allocation regression (rebased from #980) OpenAI Codex

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window8,714
Merge commits removed−27
CI / dependency bots removed−109
Considered8,578

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Rust AI coding statisticsCompare evidence across Rust repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli PerryTS/perry

Scan another repository

Try