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.

01Result

coredevices/PebbleOS ↗

coredevices/PebbleOS AI coding statistics: 57.9%

of 2,176 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

57.9% agent · top contributor 55%31 contributors

team

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

1,260

agent commits

916

other considered commits

agent contributors

55%

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

1258assisted

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: 86.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1256	57.7%
GitHub Copilot	GitHub	2	0.1%
Devin	Cognition	1	0%
Cursor Agent	Anysphere	1	0%

03Evidence

Inspect the matches

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

Matched commit samples

77c56b01 on GitHubfw/board: use stereo mic capture in all recovery buildsClaude Code
fa859943 on GitHubdrivers/vibe: play AW86225 RAM waveforms instead of CONT modeClaude Code
c363df8b on GitHubdrivers/vibe: configure the AW86225 LRA from KconfigClaude Code
506da510 on GitHubsrc/fw/apps/system/notifications: allow quick launch shortcut to wipe notiGitHub Copilot
6b2f67ef on GitHublight: turn quick launch backlight off immediatelyGitHub Copilot
4c591204 on GitHubi18n: improved german translationDevin
05d571eb on GitHubsdk: expose speaker playback limits to app SDKCursor 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	2,182
Merge commits removed	−0
CI / dependency bots removed	−6
Considered	2,176

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 →Devin commitsBrowse repositories with detected Devin 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 coredevices/PebbleOS

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	14.3%	203
2026-03	33.8%	231
2026-04	52.4%	393
2026-05	52.6%	407
2026-06	70.1%	294
2026-07	85.7%	308
2026-08	86.8%	205
2026-09	63%	135