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.

Live code review for Neovim with VSCode style diffs

01Result

esmuellert/codediff.nvim ↗

esmuellert/codediff.nvim AI coding statistics: 45.7%

of 422 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

45.7% agent · top contributor 81.3%3 contributors

individual

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

193

agent commits

229

other considered commits

agent contributors

81.3%

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

164assisted

29autonomous

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: 76.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	175	41.5%
Claude Code	Anthropic	18	4.3%

03Evidence

Inspect the matches

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

Matched commit samples

22119dc5 on GitHubfix: use NormalFloat in keymap help windowGitHub Copilot
a3350b32 on GitHubInitial planGitHub Copilot
96b7f379 on GitHubfix(gutter-signs): guard sign placement and restore move priorityGitHub Copilot
1f3267ef on GitHubfix(navigation): default cycle_hunks_across_files to false (#412)Claude Code
52c3dd43 on GitHubfeat(navigation): cycle hunks across files at ]c/[c boundary (#161)Claude Code
c1011dce on GitHubfeat(ui): sync fold open/close across diff panes in compact mode (#171)Claude 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 window	718
Merge commits removed	−199
CI / dependency bots removed	−97
Considered	422

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 →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 esmuellert/codediff.nvim

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	50%	92
2026-03	74.2%	66
2026-04	12.5%	8
2026-05	76.9%	13
2026-06	66.7%	12
2026-07	49.1%	110
2026-08	31.9%	72
2026-09	4.1%	49