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.

☸️ The Open Testing Platform for AI-Driven Engineering Teams

01Result

kubeshop/testkube ↗

kubeshop/testkube AI coding statistics: 24.4%

of 459 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
24.4% agent · top contributor 44.6%15 contributors
org-wide

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

112
agent commits
347
other considered commits
15
agent contributors
44.6%
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

93assisted
19autonomous

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
2026-0225%60
2026-0339%100
2026-0418.1%72
2026-0534%50
2026-0624.4%41
2026-0716.1%56
2026-0815.9%44
2026-095.6%36

Peak month: 39%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub8919.4%
Claude CodeAnthropic153.3%
Cursor AgentAnysphere102.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 3c875372 on GitHubfeat: support multiple events in test trigger spec (#8112)GitHub Copilot
  • 31322d39 on GitHubfeat: [TKC-6349] ai tool detection (#8024)GitHub Copilot
  • 15895e81 on GitHubfeat: [TKC-5845] 4 mcp insights mcp tools (#7974)GitHub Copilot
  • a0364744 on GitHubfeat(cli): add --org-name and --env-name login flags (#8219)Claude Code
  • 86d96b8b on GitHubfix(js): regenerate package-lock.json for the inquirer bump (#8237)Claude Code
  • e68bcecf on GitHubchore: remove dead Test/TestSuite v3 code (#8019)Claude Code
  • 80c34824 on GitHubchore(ci/cd): Move lint and tests to Testkube's Advanced Github IntegratioCursor Agent
  • 679cd692 on GitHubfeat: add scheduler policy to targeted execution contracts (#8109)Cursor Agent
  • 8e5f095f on GitHubfix: make install.sh POSIX sh compatible and verify release checksums (#79Cursor 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 window1,090
Merge commits removed−0
CI / dependency bots removed−631
Considered459

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 →Go AI coding statisticsCompare evidence across Go 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 kubeshop/testkube

Scan another repository

Try