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.

Windows companion suite for OpenClaw

01Result

openclaw/openclaw-windows-node ↗

openclaw/openclaw-windows-node AI coding statistics: 73.7%

of 1,137 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
73.7% agent · top contributor 30.9%46 contributors
org-wide

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

838
agent commits
299
other considered commits
46
agent contributors
30.9%
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

732assisted
106autonomous

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
2026-010%2
2026-0239.6%48
2026-0362.5%48
2026-0489.9%169
2026-0589.8%471
2026-0656.3%142
2026-0752.8%108
2026-0858.4%89
2026-0941.7%60

Peak month: 89.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub79770.1%
Claude CodeAnthropic443.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • 3c43751b on GitHubfix(setup): restore published mascot and center gateway choices (#1427)GitHub Copilot
  • 6466a041 on GitHubfix(local-ai): revert dedicated-memory admission caps (#1422)GitHub Copilot
  • bd9ce43b on GitHubfeat: add Microsoft Store MSIX packaging (#1328)GitHub Copilot
  • 82d4f8ad on GitHubfeat(voice): add English (GB) Northern English Male Piper voice (#1353)Claude Code
  • 621f4100 on GitHubfix(local-ai): keep routing safe across endpoint restarts (#1390)Claude Code
  • 5aff6f79 on GitHubfix(build): Piper voice preview fails in local builds with "native libraryClaude 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 window1,320
Merge commits removed−106
CI / dependency bots removed−77
Considered1,137

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 →C# AI coding statisticsCompare evidence across C# 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 openclaw/openclaw-windows-node

Scan another repository

Try