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.

The best in open-source music discovery.

01Result

lklynet/aurral ↗

lklynet/aurral AI coding statistics: 1.8%

of 1,227 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

1.8% agent · top contributor 40.9%4 contributors

team

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

agent commits

1,205

other considered commits

agent contributors

40.9%

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

22assisted

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: 6.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	15	1.2%
Claude Code	Anthropic	7	0.6%

03Evidence

Inspect the matches

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

Matched commit samples

7e44a23f on GitHubfeat(notifications): add album request notification events (#506)Cursor Agent
b23de3ca on GitHubfeat(playlist-imports): preserve imported playlist track order (#509)Cursor Agent
407a6998 on GitHubfeat(flow): add focus release year range filtering (#520)Cursor Agent
5e28f817 on GitHubfeat: deemix download client (#736)Claude Code
3b914f93 on GitHubfix(ui): add Flows to the mobile navigation menu (#728)Claude Code
7638b1e3 on GitHubdocs: document AUTH_PROXY_ADMIN_GROUPS, fix stale role-assignment descriptClaude 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	1,798
Merge commits removed	−256
CI / dependency bots removed	−315
Considered	1,227

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 lklynet/aurral

Scan another repository

Try

Month	Agent share	Considered commits
2026-01	0%	5
2026-02	0%	142
2026-03	0%	114
2026-04	0%	123
2026-05	0%	103
2026-06	1.3%	385
2026-07	4.1%	146
2026-08	6.4%	173
2026-09	0%	36