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.

This is an operating system independent implementation of iOS device features. You can run UI tests, launch or kill apps, install apps etc. with it.

01Result

danielpaulus/go-ios ↗

danielpaulus/go-ios AI coding statistics: 60.6%

of 180 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

60.6% agent · top contributor 54.1%9 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

109

agent commits

other considered commits

agent contributors

54.1%

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

109assisted

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: 91.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	107	59.4%
GitHub Copilot	GitHub	2	1.1%

03Evidence

Inspect the matches

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

Matched commit samples

c5840429 on GitHubfeat(hid): touch input over CoreDevice HID (#849)Claude Code
13f33167 on GitHubRestore the decoder guards dropped by the previous commitClaude Code
7c1df1e3 on GitHubDrop tests that did not pull their weightClaude Code
29ccdb77 on GitHubuse portable mktemp syntaxGitHub Copilot
821b3430 on GitHubhelp: improve help presentation and usageGitHub Copilot

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	285
Merge commits removed	−98
CI / dependency bots removed	−7
Considered	180

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Go AI coding statisticsCompare evidence across Go 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 danielpaulus/go-ios

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	0%	6
2026-04	16.7%	6
2026-05	33.3%	9
2026-06	48.9%	92
2026-07	66.7%	3
2026-08	91.9%	62
2026-09	50%	2