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.

Unleash the power of Java - JBang Lets Students, Educators and Professional Developers create, edit and run self-contained source-only Java programs with unprecedented ease.

01Result

jbangdev/jbang ↗

jbangdev/jbang AI coding statistics: 4.4%

of 159 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

4.4% agent · top contributor 57.1%3 contributors

individual

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

agent commits

152

other considered commits

agent contributors

57.1%

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

7assisted

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: 23.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	6	3.8%
Cursor Agent	Anysphere	1	0.6%

03Evidence

Inspect the matches

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

Matched commit samples

1695ecc5 on GitHubfix: generate correct module-info requires for JavaFX //MODULE scripts (#2Claude Code
31fa8d53 on GitHubJDK26: Put modules required by JavaFX modules on the module-path (#2511)Claude Code
fc13cad1 on GitHubfix: only show test summaries on failure to reduce noise (#2435)Claude Code
66e7bfc3 on GitHubapp catalog docs (#2404)Cursor Agent

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	162
Merge commits removed	−0
CI / dependency bots removed	−3
Considered	159

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Java AI coding statisticsCompare evidence across Java 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 jbangdev/jbang

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	5.9%	17
2026-03	23.5%	17
2026-04	0%	3
2026-05	0%	26
2026-06	4.8%	42
2026-07	0%	45
2026-08	0%	9