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.

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

01Result

OpenWhispr/openwhispr ↗

OpenWhispr/openwhispr AI coding statistics: 5.8%

of 1,542 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.8% agent · top contributor 44.9%25 contributors
org-wide

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

89
agent commits
1,453
other considered commits
25
agent contributors
44.9%
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

89assisted
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
2026-028.6%140
2026-0310.3%348
2026-040.4%284
2026-056%83
2026-062.2%46
2026-074.9%226
2026-083.2%317
2026-0913.3%98

Peak month: 13.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic815.3%
Cursor AgentAnysphere60.4%
GitHub CopilotGitHub20.1%
OpenAI CodexOpenAI10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 97bd611e on GitHubfix(ui): make every button variant a pill (#2191)Claude Code
  • 5538b463 on GitHubperf(chat): flush streamed content to state at most every 32 ms (#2171)Claude Code
  • f6d81558 on GitHubfix(chat): render GFM tables in assistant markdown (#2131)Claude Code
  • 1b68e2d8 on GitHubfix(export): normalize meeting transcript timestamps for markdown exports Cursor Agent
  • 99698bd3 on GitHubfix(export): roll SRT millisecond overflow into seconds (#1294)Cursor Agent
  • 39883e79 on GitHubfix(dictionary): prefer SQLite over stale cache on startup (#1304)Cursor Agent
  • e4e5d19d on GitHubfeat(parakeet): add NVIDIA Nemotron streaming ASR models (EN + multilinguaGitHub Copilot
  • f3e7482f on GitHubAdd Azure AI Foundry / Azure OpenAI speech-to-text support (#997)GitHub Copilot
  • fdded860 on GitHubfix(enterprise): harden AWS Bedrock error handling (#1981)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 window1,807
Merge commits removed−255
CI / dependency bots removed−10
Considered1,542

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →JavaScript AI coding statisticsCompare evidence across JavaScript 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 OpenWhispr/openwhispr

Scan another repository

Try