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.

Peach 蜜桃:单用户、本地优先的个人媒体系统 · Single-user, local-first personal media system

peach-mitao/peach ↗

peach-mitao/peach AI coding statistics: 58.6%

of 1,770 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
58.6% agent · top contributor 88.7%2 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

1,037
agent commits
733
other considered commits
2
agent contributors
88.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

1037assisted
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
2026-0833.7%585
2026-0970.9%1185

Peak month: 70.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic99156%
OpenAI CodexOpenAI492.8%

Inspect the matches

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

Matched commit samples

  • facfa6d6 on GitHubdocs(adr): ADR-0031 写明 unmountIsland 连子孙容器一起卸,BOARD_UI 去掉已删除的状态演示页Claude Code
  • 80b17a6e on GitHubdocs(web): 前端文档按「一份数据两个读者」和子孙卸载补齐Claude Code
  • 2d18ff89 on GitHubfeat(web): 扫描与采集的卡片和横幅改为 React 档Claude Code
  • aa09fb2a on GitHubfix(web): 窄屏搜索开合的聚焦不带着页面滚OpenAI Codex
  • e1d07c29 on GitHubfix(web): 完善关注与复核工具栏及采集反馈OpenAI Codex
  • 2add035a on GitHubfix(web): 完善关注分页、别名多选与响应式操作OpenAI Codex

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 window2,732
Merge commits removed−958
CI / dependency bots removed−4
Considered1,770

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

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 peach-mitao/peach

Scan another repository