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.

An open-source package that brings the power of modern headless e-commerce functionality to Laravel.

01Result

lunarphp/lunar ↗

lunarphp/lunar AI coding statistics: 22.7%

of 132 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
22.7% agent · top contributor 80%6 contributors
individual

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

30
agent commits
102
other considered commits
6
agent contributors
80%
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

30assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020%2
2026-030%8
2026-040%29
2026-050%40
2026-060%3
2026-070%4
2026-0865.2%46

Peak month: 65.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic3022.7%
Cursor AgentAnysphere10.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • a9e3b360 on GitHubfix(repo): check maintainer status via the permission API, not the payloadClaude Code
  • a3061da5 on GitHubfix(repo): exempt maintainer PRs from the nudges and guard fast mergesClaude Code
  • cd2735f5 on GitHubfix(repo): raise per-run budget caps above their operating floorClaude Code
  • cbd84d4f on GitHubFix hub product option mapping and new variant tax class (1.x) (#2640)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 window160
Merge commits removed−28
CI / dependency bots removed−0
Considered132

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 →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 lunarphp/lunar

Scan another repository

Try