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.

Next generation distributed, event-driven, parallel config management!

01Result

purpleidea/mgmt ↗

purpleidea/mgmt AI coding statistics: 37%

of 521 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

37% agent · top contributor 90.7%7 contributors

individual

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

193

agent commits

328

other considered commits

agent contributors

90.7%

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

192assisted

1autonomous

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: 61.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	120	23%
OpenAI Codex	OpenAI	71	13.6%
Other / generic agent	Various	4	0.8%
Gemini CLI	Google	1	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

1220d0d0 on GitHublang: types: Export struct field names in ReflectClaude Code
b9b5e410 on GitHubengine: resources: svc: Wait for job result then free channel explicitlyClaude Code
60fc872c on GitHubengine: resources: svc: Fix shutdown deadlock in subscription drainClaude Code
1a427045 on GitHublang: Add a live test for except operatorOpenAI Codex
cf2b1380 on GitHublang: ast: Catch possible nil panicsOpenAI Codex
bc1e08e6 on GitHublang: ast: Copy the textareaOpenAI Codex
aea315bd on GitHubtest: Enforce obj as standard method receiver nameOther / generic agent
2b61ad06 on GitHubtest: Ensure no non-standard characters in commentsOther / generic agent
ada061b6 on GitHubmisc: Rename all method receivers to standard var nameOther / generic agent
5ba8de31 on GitHubtest: Add go mod madness testGemini CLI

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	521
Merge commits removed	−0
CI / dependency bots removed	−0
Considered	521

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 purpleidea/mgmt

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	22%	41
2026-03	11.1%	45
2026-04	17.9%	39
2026-05	61.8%	123
2026-06	48.7%	113
2026-07	44.8%	67
2026-08	7.7%	78
2026-09	33.3%	15