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 distributed SQLite server with MySQL wire compatible interface

01Result

maxpert/marmot ↗

maxpert/marmot AI coding statistics: 53.4%

of 103 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

53.4% agent · top contributor 96.4%2 contributors

individual

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

agent commits

other considered commits

agent contributors

96.4%

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

55assisted

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

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	55	53.4%

03Evidence

Inspect the matches

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

Matched commit samples

07a889cf on GitHubbuild: move to Go 1.27, pin Vitess v0.23.5, bump gRPC to v1.83.2 (#172)Claude Code
2d871bc1 on GitHubfix(compat): close 21 defects blocking real MySQL clients (#171)Claude Code
9579ce4b on GitHubchore(release): bump version to v2.9.15-betaClaude 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	106
Merge commits removed	−3
CI / dependency bots removed	−0
Considered	103

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 →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 maxpert/marmot

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	11
2026-03	100%	2
2026-04	75.9%	58
2026-05	0%	23
2026-08	100%	4
2026-09	100%	5