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

microsoft/playwright ↗

microsoft/playwright AI coding statistics: 3.6%

of 1,627 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.6% agent · top contributor 56.9%12 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

58
agent commits
1,569
other considered commits
12
agent contributors
56.9%
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

47assisted
11autonomous

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
2026-020%182
2026-030.4%241
2026-043.1%290
2026-053.1%225
2026-060.9%222
2026-0712.1%232
2026-085.5%146
2026-093.4%89

Peak month: 12.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub513.1%
Claude CodeAnthropic50.3%
Cursor AgentAnysphere20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1ea94e9c on GitHubdocs(test): document mouse-outside-viewport screenshot helper (#42446)GitHub Copilot
  • e51e5b5a on GitHubtest(connect): unblock hung launchServer teardown with SIGKILL fallback (#GitHub Copilot
  • 6846dc7d on GitHubtest(mcp): de-flake annotate screencast session switch startup (#42195)GitHub Copilot
  • 9e371c00 on GitHubfeat(mcp): add --timeout-idle to close the browser after inactivity (#4266Claude Code
  • 92dcf5d3 on GitHubfix(reporter): honor NO_COLOR in list/line/dot reporters (#40903)Claude Code
  • 0aec507a on GitHubfix(mcp): handle page crash event in Tab constructor (#40426)Claude Code
  • ba0b817d on GitHubfix(trace-viewer): label filter inputs and keyboard-accessible error sourcCursor Agent
  • 2ca42d22 on GitHubfix(playwright): remove dead package.json export subpaths (#41362)Cursor Agent

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 window1,830
Merge commits removed−0
CI / dependency bots removed−203
Considered1,627

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
microsoft/playwright
Default branch
main
Resolved HEAD
18205280b6112a4a08238195942c4fa30c199a62 ↗
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.

CohortJS/TS · 376 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 194 of 570 ecosystem repositories excluded
Agent-commit share position44th percentile

Midrank percentile; equal shares split the tied positions.

Repository
3.6%
Cohort median
5.4%
Share rank
210 / 376
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 376.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 microsoft/playwright

Scan another repository

Try