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.

Native macOS control center for AI coding agents — monitor sessions, approve actions, and jump back instantly.

01Result

Octane0411/open-vibe-island ↗

Octane0411/open-vibe-island AI coding statistics: 54.5%

of 752 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

54.5% agent · top contributor 65.9%21 contributors

team

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

410

agent commits

342

other considered commits

agent contributors

65.9%

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

410assisted

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: 63.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	405	53.9%
Cursor Agent	Anysphere	5	0.7%

03Evidence

Inspect the matches

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

Matched commit samples

b3738b62 on GitHubtest: loosen CI timing bound in CodexAppServerTimeoutTestsClaude Code
38d5bdca on GitHubfix: repair a closed island that keeps swallowing clicksClaude Code
692c88e9 on GitHubfix(pi): give Pi a brand colour distinct from Grok BuildClaude Code
c109f51b on GitHubfix: reuse one Codex.app running snapshot per monitor cycleCursor Agent
bee17489 on GitHubfix: address CodeRabbit review on Codex.app reconciliationCursor Agent
2fc15442 on GitHubfix: hide archived and stale Codex.app sessions from the islandCursor 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	1,081
Merge commits removed	−269
CI / dependency bots removed	−60
Considered	752

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 →Swift AI coding statisticsCompare evidence across Swift 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 Octane0411/open-vibe-island

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	62.6%	564
2026-05	21.1%	90
2026-06	33.3%	24
2026-07	11.1%	18
2026-08	25%	20
2026-09	63.9%	36