← the index
neovim/neovim
2.6%
of 2,418 commits were committed by an AI agent — a floor, not an estimate
2.6% agent · top contributor 90.3%5 contributors
individual

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

62
agent commits
2,356
human commits
5
agent contributors
90.3%
largest contributor

Assisted or autonomous

62assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.

Agent share by month

Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 5.5%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic582.4%
Gemini CLIGoogle20.1%
DevinCognition20.1%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • 70958daevim-patch:9.2.0996: debugger: crash when evaluating a variable in a :def fClaude Code
  • 53211adevim-patch:9.2.0969: runtime(shaderslang): matchit % breaks on braces (#413Claude Code
  • bce3bf06vim-patch:9.2.0963: crash when sound-folding a crafted spell file (#41358)Claude Code
  • 60d069d4vim-patch:9.2.0445: win_fix_scroll() called before win_comp_pos() in commaGemini CLI
  • 64249d2fvim-patch:9.2.0438: tests: test_plugin_termdebug is flakyGemini CLI
  • 2926668fvim-patch:75decb4: runtime(glimmer): add syntax support for glimmer filesDevin
  • aa9ab2e7vim-patch:99ea2b5: runtime(handlebars): adds handlebars template syntax & Devin

What was excluded

Commits in window2,752
Merge commits removed252
CI / dependency bots removed82
Considered2,418

Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.

How this was measured

Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.

Run it yourself: npx qmmit-cli neovim/neovim

Scan another repository