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

jamiepine/voicebox ↗

jamiepine/voicebox AI coding statistics: 14.2%

of 346 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.2% agent · top contributor 32.7%18 contributors
org-wide

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

49
agent commits
297
other considered commits
18
agent contributors
32.7%
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

49assisted
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
2026-0214.7%34
2026-030%197
2026-0444.6%65
2026-0613.3%15
2026-0737.1%35

Peak month: 44.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic4613.3%
Cursor AgentAnysphere30.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • 80610d88 on GitHubfix(ui): open FloatingGenerateBox selects upward to prevent clipping (fixeClaude Code
  • 1ba935e8 on GitHubfix(export): disambiguate export filenames with generation id (#956)Claude Code
  • 6a6f4643 on GitHubfix(backend): guard avatar upload against a missing filename (#954)Claude Code
  • 30db291b on GitHubfix(kokoro): add missing male Mandarin voices (#788)Cursor Agent
  • cabef1bf on GitHubfix(docker): add ROCm GPU support via compose overlay (#630)Cursor Agent
  • 0be7975d on GitHubfix: handle non-ASCII filenames in Content-Disposition headersCursor 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 window409
Merge commits removed−63
CI / dependency bots removed−0
Considered346

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
jamiepine/voicebox
Default branch
main
Resolved HEAD
51f49dea198384b4eb6087b72c17057c6eb1c1cd ↗
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.

CohortJS/TS · 376 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 194 of 570 ecosystem repositories excluded
Agent-commit share position70th percentile

Midrank percentile; equal shares split the tied positions.

Repository
14.2%
Cohort median
5.4%
Share rank
113 / 376
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 376.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code 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 jamiepine/voicebox

Scan another repository

Try