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 TypeScript superset that favors more types and less typing

01Result

DanielXMoore/Civet ↗

DanielXMoore/Civet AI coding statistics: 53.4%

of 985 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
53.4% agent · top contributor 85.9%4 contributors
individual

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

526
agent commits
459
other considered commits
4
agent contributors
85.9%
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

457assisted
69autonomous

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%44
2026-0310.7%28
2026-0432%200
2026-0573.4%575
2026-0648.5%66
2026-0720%20
2026-083.1%32
2026-090%20

Peak month: 73.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic52353.1%
GitHub CopilotGitHub30.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • e41c4003 on GitHubFix export default with nested implicit object literal (#2186)Claude Code
  • 2b0db771 on GitHubfix: don't crash on empty-braces property definitions or invalid globsClaude Code
  • a267a439 on GitHubFix implicitElse type-check regression, document []-fallbackClaude Code
  • cf7cab74 on GitHubFix: semicolon-terminated single-line case clause fails to parse (#1889)GitHub Copilot
  • 73ac72c5 on GitHubFix parse error for trailing comments in JSX prop function bodies (#1887)GitHub Copilot
  • 8bbb6b93 on GitHubFix one-line arrow dynamic import parsing (#1884)GitHub Copilot

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 window1,200
Merge commits removed−211
CI / dependency bots removed−4
Considered985

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 DanielXMoore/Civet

Scan another repository

Try