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.

Free Windows, Mac and Linux cleaner, scanner, and more.

01Result

AdventDevInc/kudu ↗

AdventDevInc/kudu AI coding statistics: 57%

of 444 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
57% agent · top contributor 95.3%6 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

253
agent commits
191
other considered commits
6
agent contributors
95.3%
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

253assisted
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
2026-0376%271
2026-0474.1%27
2026-0578.9%19
2026-060%3
2026-0710%20
2026-082.2%46
2026-0915.5%58

Peak month: 78.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic24555.2%
Cursor AgentAnysphere40.9%
GitHub CopilotGitHub40.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7582112e on GitHubfix(restore-point): say when System Protection is off instead of relaying Claude Code
  • 4e804f8c on GitHubfeat(i18n): default to the OS language on a fresh install (#407)Claude Code
  • 2235920e on GitHubfix(cli): report failed operations through the exit code (#409)Claude Code
  • f23f2de0 on GitHubfix(malware): show fixed scan roots and extensions in UI (#393)Cursor Agent
  • d10617c1 on GitHubfix(ipc): omit parent window for Linux folder dialogs (#392)Cursor Agent
  • 6e780814 on GitHubfix(malware): trust Mozilla Firefox folders and vendor install dirs (#385)Cursor Agent
  • 4bccf8d3 on GitHubPotential fix for code scanning alert no. 6: Workflow does not contain perGitHub Copilot
  • dad99ba4 on GitHubPotential fix for code scanning alert no. 4: Workflow does not contain perGitHub Copilot
  • d010e8ba on GitHubPotential fix for code scanning alert no. 5: Workflow does not contain perGitHub 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 window524
Merge commits removed−23
CI / dependency bots removed−57
Considered444

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 AdventDevInc/kudu

Scan another repository

Try