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.

nightscout web monitor

01Result

nightscout/cgm-remote-monitor ↗

nightscout/cgm-remote-monitor AI coding statistics: 28.1%

of 392 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

28.1% agent · top contributor 92.7%7 contributors

individual

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

110

agent commits

282

other considered commits

agent contributors

92.7%

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

108assisted

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

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	107	27.3%
Claude Code	Anthropic	3	0.8%

03Evidence

Inspect the matches

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

Matched commit samples

f6264a33 on GitHubfix(security): purify API v3 writesGitHub Copilot
72a2257e on GitHubfix(security): purify API v3 writesGitHub Copilot
1433a673 on GitHubtest(loop): cover APNs profile environment selectionGitHub Copilot
dee62a92 on GitHubDon't snooze high alarm when there is no IOB (#6348)Claude Code
ba184798 on GitHubfeat(client): add 48-hour option to focus range selectorClaude Code
c457817a on GitHubAddress maintainer feedback on webhook pluginClaude 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	579
Merge commits removed	−167
CI / dependency bots removed	−20
Considered	392

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 →JavaScript AI coding statisticsCompare evidence across JavaScript 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 nightscout/cgm-remote-monitor

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	80%	5
2026-03	71.1%	83
2026-04	63.6%	11
2026-05	32%	100
2026-06	100%	2
2026-07	40%	10
2026-08	0%	8
2026-09	1.2%	173