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.

Local speech-to-text for macOS on-device AI, fully private, optional cloud

01Result

TypeWhisper/typewhisper-mac ↗

TypeWhisper/typewhisper-mac AI coding statistics: 1.8%

of 1,059 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.8% agent · top contributor 26.3%9 contributors
org-wide

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

19
agent commits
1,040
other considered commits
9
agent contributors
26.3%
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

19assisted
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
2026-020.4%223
2026-031.3%151
2026-041.6%187
2026-050%115
2026-061.1%94
2026-071.8%113
2026-084.1%122
2026-099.3%54

Peak month: 9.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic111%
GitHub CopilotGitHub40.4%
OpenAI CodexOpenAI40.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • d86c1035 on GitHubBound the final-transcription phase with a deadline (resubmission of #1246Claude Code
  • 2e407c5c on GitHubAdd hedged transcription: race the recovery fallback when the primary engiClaude Code
  • 309eea91 on GitHubFix notch indicator crash from SwiftUI animating the panel window inside lClaude Code
  • 6c1747ba on GitHubSupport deployment-scoped compatible transcription (#1112)GitHub Copilot
  • 71aef292 on GitHubAdd Responses API to OpenAI Compatible plugin (#1101)GitHub Copilot
  • 8cd49741 on GitHubAdd realtime transcription support to OpenAI Compatible plugin (#1052)GitHub Copilot
  • e22a9bac on GitHubFix Parakeet language filtering with FluidAudio upstream (#392)OpenAI Codex
  • 75a6dd01 on GitHubfix: preserve focus during local prompt processing (#398)OpenAI Codex
  • 31e00161 on GitHubfeat: group menu bar menu sections (#397)OpenAI Codex

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 window1,228
Merge commits removed−137
CI / dependency bots removed−32
Considered1,059

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Swift AI coding statisticsCompare evidence across Swift 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 TypeWhisper/typewhisper-mac

Scan another repository

Try