Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

iOfficeAI/OfficeCLI ↗

iOfficeAI/OfficeCLI AI coding statistics: 1.1%

of 6,014 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.1% agent · top contributor 32.4%10 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

68
agent commits
5,946
other considered commits
10
agent contributors
32.4%
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

68assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-033.4%645
2026-042.4%1436
2026-050.3%1486
2026-060.2%1681
2026-070.6%699
2026-080%29
2026-090%38

Peak month: 3.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic591%
GitHub CopilotGitHub90.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 2b9b5ee1 on GitHubfix(pptx): duplicated notes keep their own pictures and hyperlinksClaude Code
  • 96253d59 on GitHubfix(pptx): speaker notes get a notes master to inherit fromClaude Code
  • 6cbf7843 on GitHubfix(cli): decode piped stdin as UTF-8 without mutating the consoleClaude Code
  • 74e18b36 on GitHubfix(preview): deduplicate heading numbers when text already contains themGitHub Copilot
  • 9e5e7c85 on GitHubfeat(preview): convert EMF/WMF to PNG for browser renderingGitHub Copilot
  • f6b0af5c on GitHubfeat(word-preview): add OLE object preview and heading auto-numberingGitHub 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 window6,123
Merge commits removed−109
CI / dependency bots removed−0
Considered6,014

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
iOfficeAI/OfficeCLI
Default branch
main
Resolved HEAD
5a938d2d111ba1873452575c6e3fadb3dd0caae8 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortC# · 21 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 10 of 31 ecosystem repositories excluded
Agent-commit share position26th percentile

Midrank percentile; equal shares split the tied positions.

Repository
1.1%
Cohort median
2.1%
Share rank
16 / 21
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 21.

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 iOfficeAI/OfficeCLI

Scan another repository

Try