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.

🐸 Read Frog - Open-source AI language learning & flashcards, an Immersive Translate alternative | 🐸 陪读蛙 - 开源 AI 语言学习与闪词卡，沉浸式翻译替代

01Result

mengxi-ream/read-frog ↗

mengxi-ream/read-frog AI coding statistics: 30.9%

of 527 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
30.9% agent · top contributor 36.8%11 contributors
org-wide

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

163
agent commits
364
other considered commits
11
agent contributors
36.8%
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

163assisted
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
2026-0258.1%62
2026-0318.2%99
2026-043.1%65
2026-059.5%42
2026-0618.4%49
2026-0735.8%120
2026-0859.6%57
2026-0951.5%33

Peak month: 59.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic16230.7%
Cursor AgentAnysphere20.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 51418860 on GitHubfix(subtitles): keep YouTube subtitles on screen after the miniplayer leavClaude Code
  • 788afe30 on GitHubfeat(prompts): link the prompt editors to the variable reference (#2187)Claude Code
  • f5541ff6 on GitHubfix(glossary): say that a website pattern can also end in a wildcard (#218Claude Code
  • 80bd105d on GitHubfix(translate): stop page-translation flicker on same-origin navigation (#Cursor Agent
  • 80aeb349 on GitHubfeat(subtitles): export translated srt (#1624)Cursor 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 window686
Merge commits removed−14
CI / dependency bots removed−145
Considered527

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 mengxi-ream/read-frog

Scan another repository

Try