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.

SSH workspace, SFTP, and terminals in one

01Result

binaricat/Netcatty ↗

binaricat/Netcatty AI coding statistics: 24.3%

of 4,147 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
24.3% agent · top contributor 59.1%23 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

1,006
agent commits
3,141
other considered commits
23
agent contributors
59.1%
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

1004assisted
2autonomous

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
2026-0237.8%90
2026-0359.6%616
2026-0466.8%229
2026-0541.6%166
2026-0627.9%621
2026-078.3%1307
2026-0810.5%880
2026-094.2%238

Peak month: 66.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic67216.2%
Cursor AgentAnysphere3177.6%
GitHub CopilotGitHub200.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • d92406a9 on GitHubfix(auto-launch): 补齐跨窗口同步、修正连续切换的陈旧响应竞态Claude Code
  • 7c419f41 on GitHubfix(auto-launch): 修正写入失败回滚、挂载竞态、隐藏启动焦点竞态Claude Code
  • 151364ce on GitHubfix(auto-launch): 修正 macOS 待审批状态误触发禁用与 Linux 文案Claude Code
  • 8017c144 on GitHubfeat(cli): bind Skills+CLI chat session via host env (#3347)Cursor Agent
  • 891faff3 on GitHubfeat(workspace): search hosts by tag (#3001) (#3337)Cursor Agent
  • d920d076 on GitHubfix(workspace): hand focus to a remaining session when closing the focusedCursor Agent
  • a1b1c37f on GitHubUpdate Chinese and Japanese READMEs to match English README (#1894)GitHub Copilot
  • fa3f17fa on GitHubfix(autocomplete): prevent popup from rendering below visible terminal scrGitHub Copilot
  • 5a1d6931 on GitHubFix Tab completion preferring history over local files (#867)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 window4,938
Merge commits removed−775
CI / dependency bots removed−16
Considered4,147

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 →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 binaricat/Netcatty

Scan another repository

Try