Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

debpalash/VoiceStudio ↗

debpalash/VoiceStudio AI coding statistics: 51.8%

of 1,912 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
51.8% agent · top contributor 70.7%28 contributors
team

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

991
agent commits
921
other considered commits
28
agent contributors
70.7%
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

991assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0430.1%113
2026-0571.5%123
2026-0690.6%363
2026-0782.3%457
2026-0811.2%455
2026-0928.2%401

Peak month: 90.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic98751.6%
Cursor AgentAnysphere40.2%
GitHub CopilotGitHub30.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 25393b46 on GitHubtest(worker): stop spinning the loop the awaited work needsClaude Code
  • e1127099 on GitHubfix(backend): identify the port holder by the marker header, not a body snClaude Code
  • f21ad9a2 on GitHubfix(crash): close the far end of a dead run's slice, and settle one at a tClaude Code
  • 37aea507 on GitHubfix(setup): lengthen HF connectivity probe timeouts to 8sCursor Agent
  • 9979f1a8 on GitHubfix(bootstrap): apply China PyPI mirror on repair uv syncCursor Agent
  • 9d30774e on GitHubfeat(audiobook): synced lyrics playback (#1766)Cursor Agent
  • c0924f5e on GitHubfix(tts): torch.compile failures fall back to eager — generation never faiGitHub Copilot
  • 853b9eef on GitHubfix(dub): burn translated subtitles, fix subtitle save JSON error (#309) (GitHub Copilot
  • 48ae4dae on GitHubfix(dub): re-dub honors transcript edits — fingerprints canonicalised, preGitHub 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 window2,540
Merge commits removed−613
CI / dependency bots removed−15
Considered1,912

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

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
debpalash/VoiceStudio
Default branch
main
Resolved HEAD
8a1e6eb0586643746deee1a513df0ed13c6c9709 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position93rd percentile

Midrank percentile; equal shares split the tied positions.

Repository
51.8%
Cohort median
6.3%
Share rank
18 / 247
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 247.

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 →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 debpalash/VoiceStudio

Scan another repository

Try