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.

A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents — so you don't have to.

01Result

rullerzhou-afk/clawd-on-desk ↗

rullerzhou-afk/clawd-on-desk AI coding statistics: 26.4%

of 1,984 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
26.4% agent · top contributor 77.8%46 contributors
team

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

523
agent commits
1,461
other considered commits
46
agent contributors
77.8%
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

523assisted
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
2026-0395.9%243
2026-0453%368
2026-0512.1%365
2026-0611.8%203
2026-073.4%350
2026-083%363
2026-094.3%92

Peak month: 95.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic51325.9%
Cursor AgentAnysphere70.4%
GitHub CopilotGitHub30.2%
OpenAI CodexOpenAI20.1%
Gemini CLIGoogle20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 41dfe837 on GitHubtest(linux): tighten #979 fixtures and helper commentClaude Code
  • aa7fbfc0 on GitHubfix(linux): address review on all-workspaces pinningClaude Code
  • b077bb94 on GitHubfeat(permissions): opt-in reminder that holds destructive requests under aClaude Code
  • 8f1ea52a on GitHubfix(feishu): resolve remote approval recipients by email (#750)Cursor Agent
  • 7df5a386 on GitHubfix(telegram): claim approval decision atomically before card rewrite (PR Cursor Agent
  • e8df7d7a on GitHubfeat(telegram): rewrite approval card with outcome on Telegram-side taps tCursor Agent
  • 15655e74 on GitHubl10n: improve translation of zh-TW (#310)GitHub Copilot
  • 3dc6be9c on GitHubfeat(remote-deploy): auto-register Copilot CLI hooks on SSH remotesGitHub Copilot
  • eacb8c3c on GitHubfeat(copilot-hook): forward Copilot CLI session name to Clawd (#267)GitHub Copilot
  • 0f973ecc on GitHubfix: address follow-up review on runtime and hook safetyOpenAI Codex
  • 7c752ba8 on GitHubfix: harden macOS focus, hook sync, and local server reliabilityOpenAI Codex
  • 0f973ecc on GitHubfix: address follow-up review on runtime and hook safetyGemini CLI
  • 7c752ba8 on GitHubfix: harden macOS focus, hook sync, and local server reliabilityGemini CLI

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 window2,375
Merge commits removed−391
CI / dependency bots removed−0
Considered1,984

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 rullerzhou-afk/clawd-on-desk

Scan another repository

Try