Pulse
2026-09-18-v3.0
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.

⛷ A quiet, local-first Markdown writing app for Mac, to help you write great sentences.

01Result

tw93/MiaoYan ↗

tw93/MiaoYan AI coding statistics: 7.7%

of 352 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
7.7% agent · top contributor 77.8%3 contributors
individual

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

27
agent commits
325
other considered commits
3
agent contributors
77.8%
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

27assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020%57
2026-0313.4%67
2026-040%61
2026-0523.7%76
2026-060%48
2026-070%30
2026-080%7
2026-090%6

Peak month: 23.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere123.4%
GitHub CopilotGitHub92.6%
Claude CodeAnthropic61.7%

03Evidence

Inspect the matches

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

Matched commit samples

  • 30d1c5f7 on GitHubchore: clean up regex declarations and fix stale doc commentCursor Agent
  • 7ca11697 on GitHubfix: snapshot URL encoding for paths with spaces + symlink perfCursor Agent
  • 642de94f on GitHubfix: eliminate dark mode flash on first/second note openCursor Agent
  • 51d20352 on GitHubfix: remove Cmd+J interception in NotesTableView.performKeyEquivalentGitHub Copilot
  • 8f255394 on GitHubfix: openInTerminal uses ViewController.shared() to avoid proxy nil-outletGitHub Copilot
  • 2562b628 on GitHubfix: Open in Terminal main menu target must use App Scene proxy L4m-js-agnGitHub Copilot
  • 6a3c591d on GitHubfix: search uPic placeholder over UTF-16 length, not String.countClaude Code
  • 453b3ccf on GitHubfeat: add font zoom shortcuts (⌘=/⌘-/⌘0) for editor and previewClaude Code
  • e086c6a5 on GitHubfix: fall back to note.content when placeholder not found in textStorageClaude 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 window355
Merge commits removed−3
CI / dependency bots removed−0
Considered352

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 →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 tw93/MiaoYan

Scan another repository

Try