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.

plakar is a backup solution powered by Kloset and ptar

01Result

PlakarKorp/plakar ↗

PlakarKorp/plakar AI coding statistics: 15.8%

of 349 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

15.8% agent · top contributor 80%4 contributors

individual

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

agent commits

294

other considered commits

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

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: 32.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	55	15.8%

03Evidence

Inspect the matches

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

Matched commit samples

b65f2e14 on GitHublogin: name the error-body read limitClaude Code
8219560d on GitHublogin: cap the 401 body read in isCompletionCodeRequiredClaude Code
964e0783 on GitHubaddress review: drop the adapter and the checksum indirectionClaude 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	677
Merge commits removed	−270
CI / dependency bots removed	−58
Considered	349

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 PlakarKorp/plakar

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	29
2026-03	5.8%	52
2026-04	5.6%	18
2026-05	28%	75
2026-06	32.3%	62
2026-07	0%	23
2026-08	11.4%	70
2026-09	10%	20