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.

:gem: Go! AOP PHP - modern aspect-oriented framework for the new level of software development

01Result

goaop/framework ↗

goaop/framework AI coding statistics: 87.6%

of 242 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

87.6% agent · top contributor 57.5%6 contributors

team

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

212

agent commits

other considered commits

agent contributors

57.5%

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

206assisted

6autonomous

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	196	81%
GitHub Copilot	GitHub	10	4.1%
Devin	Cognition	6	2.5%

03Evidence

Inspect the matches

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

Matched commit samples

80b36ce1 on GitHubrefactor: give the trait and alias markers distinct namesClaude Code
9ea00418 on GitHubrefactor: replace the `__aop__` prefix with an `Original` suffix in generaClaude Code
824a96e2 on GitHubdocs(agents): keep the remote-session section to the phpstan install onlyClaude Code
d4eacd04 on GitHubInitial planGitHub Copilot
547f3775 on GitHubfeat: add by-ref test for ReflectionFunctionInvocation, update CLAUDE.md aGitHub Copilot
d7a32a19 on GitHubfeat: Add return type as second generic variable to core interfaces (#551)GitHub Copilot
86a3bdd6 on GitHubDocument why hooked properties cannot be intercepted (F3)Devin
ef1ee6c2 on GitHubDocument PHP 8.4 limitations: hooked properties, lazy objects, readonlyDevin
976ca100 on GitHubAdd test for #[\Deprecated] attribute propagation through proxiesDevin

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	330
Merge commits removed	−84
CI / dependency bots removed	−4
Considered	242

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 →Devin commitsBrowse repositories with detected Devin signatures →PHP AI coding statisticsCompare evidence across PHP 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 goaop/framework

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	87%	77
2026-04	52%	25
2026-05	46.2%	13
2026-06	50%	2
2026-07	100%	5
2026-08	100%	54
2026-09	100%	66