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.

A Lean companion to Analysis I

01Result

teorth/analysis ↗

teorth/analysis AI coding statistics: 46.6%

of 324 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

46.6% agent · top contributor 76.2%5 contributors

team

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

151

agent commits

173

other considered commits

agent contributors

76.2%

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

149assisted

2autonomous

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: 91.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	115	35.5%
Claude Code	Anthropic	34	10.5%
GitHub Copilot	GitHub	2	0.6%

03Evidence

Inspect the matches

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

Matched commit samples

cb9108f7 on GitHubfix: add Verso doc comment periods in Section_1_2_2Cursor Agent
16d59988 on GitHubfix: disambiguate Verso labels in Section 6.1Cursor Agent
7e01fd0a on GitHubfix: disambiguate Verso labels in Section 9.1Cursor Agent
630d701c on GitHubfeat(MeasureTheory): extended-real Jordan inner measure for Exercise 1.2.5Claude Code
92bc4a73 on GitHubAlso space the Verso closer on the relabelled line, per #621Claude Code
c78c18ab on GitHubMeasure theory 1.2.2: Exercises 1.2.18 and 1.2.22 have two parts, not threClaude Code
b1dd6fa7 on GitHubFix corrupted Lake cache handling in build workflowGitHub Copilot
31252c47 on GitHubInitial planGitHub 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	534
Merge commits removed	−210
CI / dependency bots removed	−0
Considered	324

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →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 teorth/analysis

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	91.7%	12
2026-03	7.4%	27
2026-04	33.3%	21
2026-05	63.6%	11
2026-06	75%	36
2026-07	89.5%	95
2026-08	13.8%	80
2026-09	2.4%	42