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.

See interfaces like a human. E2E testing in natural language.

01Result

web-infra-dev/midscene ↗

web-infra-dev/midscene AI coding statistics: 7.8%

of 734 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
7.8% agent · top contributor 35.1%12 contributors
org-wide

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

57
agent commits
677
other considered commits
12
agent contributors
35.1%
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

57assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0221.4%84
2026-0323.4%111
2026-043.1%97
2026-050%87
2026-067%114
2026-071%98
2026-080%92
2026-092%51

Peak month: 23.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic527.1%
Cursor AgentAnysphere40.5%
GitHub CopilotGitHub20.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 56e1d851 on GitHubfeat(shared): support reference images in the act CLI tool (#2871)Claude Code
  • 4cf3a667 on GitHubrefactor: separate aiAct progress data from presentation logic (#2707)Claude Code
  • 94d26fd4 on GitHubAdd collapsible reasoning section to detail panel (#1894)Claude Code
  • c5c9d013 on GitHubdocs(core): update overview for test runner (#3092)Cursor Agent
  • 6efd3a72 on GitHub[codex] Merge PR 2520 with review follow-ups (#2554)Cursor Agent
  • 754f94a2 on GitHubfeat(core): log execution log on disk (#2245)Cursor Agent
  • 07461e19 on GitHubfix(playwright): guard against undefined page in PlaywrightAgent/PuppeteerGitHub Copilot
  • fe9f9c7f on GitHubfix(core): prevent YAML folded block scalar (>-) from corrupting cache XPaGitHub 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 window818
Merge commits removed−1
CI / dependency bots removed−83
Considered734

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →TypeScript AI coding statisticsCompare evidence across TypeScript repositories →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 web-infra-dev/midscene

Scan another repository

Try