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 modern PHP app server

01Result

php/frankenphp ↗

php/frankenphp AI coding statistics: 8.2%

of 220 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

8.2% agent · top contributor 61.1%5 contributors

team

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

agent commits

202

other considered commits

agent contributors

61.1%

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

15assisted

3autonomous

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: 20%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	13	5.9%
Claude Code	Anthropic	5	2.3%

03Evidence

Inspect the matches

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

Matched commit samples

1f216dd0 on GitHubfix: feat: add php_server's env vars to sandboxed environment (#2451)GitHub Copilot
68573a9b on GitHubci: run golangci-lint on the Caddy module (#2397)GitHub Copilot
eeaab63a on GitHubci: disable dockerhub GHA env (#2369)GitHub Copilot
e768b59d on GitHubci: rebuild only Docker variants whose bases changed and make images reproClaude Code
bcc944a4 on GitHubchore: better preflight checks in release.sh (#2348)Claude Code
cda58d22 on GitHubfix(windows): ensure DLLs can always be located by PHP (#2227)Claude Code

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	244
Merge commits removed	−0
CI / dependency bots removed	−24
Considered	220

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 php/frankenphp

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	4.7%	43
2026-03	20%	50
2026-04	13.3%	15
2026-05	4.1%	49
2026-06	0%	16
2026-07	3.6%	28
2026-08	6.3%	16
2026-09	0%	3