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.

Vim - the text editor - for macOS

01Result

macvim-dev/macvim ↗

macvim-dev/macvim AI coding statistics: 14.8%

of 1,631 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.8% agent · top contributor 75.6%17 contributors
team

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

242
agent commits
1,389
other considered commits
17
agent contributors
75.6%
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

242assisted
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
2026-021%198
2026-035.1%255
2026-047.4%216
2026-0514.2%226
2026-0611.3%238
2026-0723%178
2026-0837.9%206
2026-0928.9%114

Peak month: 37.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic23214.2%
GitHub CopilotGitHub60.4%
Gemini CLIGoogle30.2%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 722c9012 on GitHubpatch 9.2.1111: Crash in a zero-width window with a status lineClaude Code
  • 24e2cf43 on GitHubpatch 9.2.1109: Popup image is drawn over a popup with a higher zindexClaude Code
  • 9e80ca3c on GitHubpatch 9.2.1105: tests: Test_lsp_incomplete_message_while_blocked fails on Claude Code
  • a96c3bc1 on GitHubruntime(robot): Include ftplugin and set comment optionsGitHub Copilot
  • 852cc912 on GitHubpatch 9.2.0758: pum: No opacity when background not set for Popup menu groGitHub Copilot
  • bc2141d2 on GitHubruntime(2html): Convert to Vim9 scriptGitHub Copilot
  • 40fc78f0 on GitHubpatch 9.2.0445: win_fix_scroll() called before win_comp_pos() in command_hGemini CLI
  • 20a124a6 on GitHubpatch 9.2.0438: tests: test_plugin_termdebug is flakyGemini CLI
  • 6146f338 on GitHubpatch 9.2.0410: test suite races when run with parallel makeGemini CLI
  • 2173c3e4 on GitHubpatch 9.2.1107: getregionpos() is slow when only the region bounds are neeCursor 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 window1,664
Merge commits removed−12
CI / dependency bots removed−21
Considered1,631

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 macvim-dev/macvim

Scan another repository

Try