← the index
neoclide/coc.nvim
5.9%
of 410 commits were committed by an AI agent — a floor, not an estimate
5.9% agent · top contributor 75%3 contributors
individual

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

24
agent commits
386
human commits
3
agent contributors
75%
largest contributor

Assisted or autonomous

24assisted
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: 33.3%. Bars are scaled to that peak, not to 100%.

Which agents

GitHub CopilotGitHub143.4%
OpenAI CodexOpenAI102.4%

Verify it yourself

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

  • afafbe7ddocs: clarify suggest insert modeGitHub Copilot
  • 1321bc8brefactor: replace strip-ansi with util.stripVTControlCharactersGitHub Copilot
  • 9358684arefactor: replace uuid package with global crypto.randomUUIDGitHub Copilot
  • cf1e7ea2fix(extension): escape installer buffer name (#5748)OpenAI Codex
  • 95d904a8fix(events): separate WinClosed and BufWinLeave (#5711)OpenAI Codex
  • 9d81c055fix(compat): optional opts argument on nvim 0.13+ (#5713)OpenAI Codex

What was excluded

Commits in window418
Merge commits removed0
CI / dependency bots removed8
Considered410

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 neoclide/coc.nvim

Scan another repository