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.

C# application to switch default playing device. Download: https://soundswitch.aaflalo.me/

Belphemur/SoundSwitch ↗

Belphemur/SoundSwitch AI coding statistics: 29.5%

of 369 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
29.5% agent · top contributor 75.2%4 contributors
team

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

109
agent commits
260
other considered commits
4
agent contributors
75.2%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

27assisted
82autonomous

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
2026-0316.7%42
2026-0473.2%41
2026-0539.7%121
2026-0653.7%41
2026-073.8%26
2026-081.1%89
2026-090%9

Peak month: 73.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub10929.5%

Inspect the matches

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

Matched commit samples

  • 7274b934 on GitHubfix(installer): bump required .NET runtime to 10.0.11GitHub Copilot
  • d39b88fc on GitHubfix(profile): Add reset per-app audio settings on profile switch (#2262)GitHub Copilot
  • 1adb6596 on GitHubDetect exclusive fullscreen and fallback to native Windows Toast notificatGitHub Copilot

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 window855
Merge commits removed−187
CI / dependency bots removed−299
Considered369

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 Belphemur/SoundSwitch

Scan another repository