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.

The `npx serve` of Apple Simulators.

01Result

EvanBacon/serve-sim ↗

EvanBacon/serve-sim AI coding statistics: 39.5%

of 129 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

39.5% agent · top contributor 92.2%4 contributors

individual

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

agent commits

other considered commits

agent contributors

92.2%

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

51assisted

0autonomous

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

Peak month: 75%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	48	37.2%
Cursor Agent	Anysphere	3	2.3%

03Evidence

Inspect the matches

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

Matched commit samples

7f109fb0 on GitHubci: pin bun version via .bun-version file (#133)Claude Code
c8206925 on GitHubfix(serve-sim): send plain R to reload RN/Expo bundle (#126)Claude Code
1cfe9900 on GitHubAdd sim reboot-and-retry to publish workflow tests (#118)Claude Code
7e44584b on GitHubfix(serve-sim): exit detached helpers after simulator shutdown (#152)Cursor Agent
bfa54734 on GitHubfix(serve-sim): stop Connecting… flash when toggling device frame (#151)Cursor Agent
48bd7959 on GitHubAllow hiding the device frame/bezel in the preview UI (#149)Cursor Agent

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 window	165
Merge commits removed	−4
CI / dependency bots removed	−32
Considered	129

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 EvanBacon/serve-sim

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	41.2%	17
2026-05	40.4%	52
2026-06	39.1%	46
2026-07	28.6%	7
2026-08	0%	3
2026-09	75%	4