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.

From git log to SemVer in no time

01Result

GitTools/GitVersion ↗

GitTools/GitVersion AI coding statistics: 24.6%

of 414 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

24.6% agent · top contributor 80.4%4 contributors

individual

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

102

agent commits

312

other considered commits

agent contributors

80.4%

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

87assisted

15autonomous

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: 63.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	82	19.8%
GitHub Copilot	GitHub	20	4.8%

03Evidence

Inspect the matches

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

Matched commit samples

814aae00 on GitHubci(git): test docker images and artifacts against both git backendsClaude Code
20d126f2 on GitHubdocs: document the git backend selection and v7 defaultsClaude Code
5fe6e5fe on GitHubci: run the unit-test matrix against both git backendsClaude Code
1814cb55 on GitHubbuild(deps): bump NUnit3TestAdapter from 6.1.0 to 6.2.0GitHub Copilot
1eacb907 on GitHubchore(deps): bump SharpYaml from 3.4.0 to 3.7.0GitHub Copilot
0a00d230 on GitHubchore(deps): bump coverlet.MTP from 8.0.1 to 10.0.0GitHub 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	832
Merge commits removed	−248
CI / dependency bots removed	−170
Considered	414

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 →C# AI coding statisticsCompare evidence across C# 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 GitTools/GitVersion

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	17.8%	45
2026-03	12.3%	73
2026-04	33.3%	9
2026-06	63.5%	96
2026-07	6.7%	105
2026-08	26.9%	52
2026-09	0%	34