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.

Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。

01Result

makecindy/cindy ↗

makecindy/cindy AI coding statistics: 19%

of 4,163 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
19% agent · top contributor 18.3%59 contributors
org-wide

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

791
agent commits
3,372
other considered commits
59
agent contributors
18.3%
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

791assisted
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
2026-0738.2%833
2026-0819.3%2431
2026-090.6%899

Peak month: 38.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic76818.4%
OpenAI CodexOpenAI130.3%
Cursor AgentAnysphere70.2%
GitHub CopilotGitHub60.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 3a08da17 on GitHubfix(pi): 修正 Anthropic OAuth 请求构造并保留原生 beta 头 (#4031)Claude Code
  • 83af0fc8 on GitHubfeat(settings): 新增「用量历史」tab，统计 Cindy 内的 token 消耗 (#3252)Claude Code
  • 1e9f9543 on GitHubfeat(login): 接入邮箱登录人机验证 (#3000)Claude Code
  • 4fd0926d on GitHubfix(scheduler): reject malformed cron expressions safely (#2122)OpenAI Codex
  • 4fd0df6c on GitHubfix(desktop): 修复 Windows 中文输入预览时标点抖动 (#894)OpenAI Codex
  • 8aedb3a7 on GitHubfix(desktop): 修复 Windows 文件拖入附件 (#756)OpenAI Codex
  • eb1a441b on GitHubfix(session): isolate Host recovery and defer cross-process Pi retirementCursor Agent
  • 2b678db2 on GitHubtest(desktop): relax Windows stale-takeover wall-clock boundCursor Agent
  • 24539b92 on GitHubfix(session): bound hung stall abort and isolate retirement recoveryCursor Agent
  • 38320a71 on GitHubfix(desktop): restore sidebar split drag for project sessions (#2052)GitHub Copilot
  • ea3ea36c on GitHubfeat(desktop): CC Agent 任务视图支持递归分屏拖拽布局 (#1632)GitHub Copilot
  • c603932b on GitHubfeat(desktop): 菜单「帮助」增加「安装到命令行」，对齐 VS Code 的 code 命令 (#1258)GitHub Copilot

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 window4,787
Merge commits removed−623
CI / dependency bots removed−1
Considered4,163

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 →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 makecindy/cindy

Scan another repository

Try