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.

Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace MCP Server & CLI Tool

01Result

taylorwilsdon/google_workspace_mcp ↗

taylorwilsdon/google_workspace_mcp AI coding statistics: 16.5%

of 1,142 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
16.5% agent · top contributor 28%53 contributors
org-wide

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

189
agent commits
953
other considered commits
53
agent contributors
28%
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

187assisted
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
2026-029.2%206
2026-0321.2%165
2026-0423.7%262
2026-053.2%125
2026-0630.9%68
2026-0719.3%88
2026-0816%163
2026-097.7%65

Peak month: 30.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic17315.1%
Cursor AgentAnysphere111%
GitHub CopilotGitHub50.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8f5587d3 on GitHubfix(gdrive): fetch shared-drive organizers sequentially to avoid SSL crashClaude Code
  • feee51bd on GitHubfix: run_script_function must use a deployment ID, not the project IDClaude Code
  • f4a33d7c on GitHubdocs: point contributors at the same ruff CI runsClaude Code
  • 19bd8a81 on GitHubfix: enforce file-byte cap before Gmail/Chat/Docs downloads completeCursor Agent
  • 20069e00 on GitHubstyle: apply ruff format to file-limit testsCursor Agent
  • d8529429 on GitHubfix: stream capped Drive downloads so export_media cannot bypass the byte Cursor Agent
  • 32d0cf84 on GitHubfeat: default user_google_email to USER_GOOGLE_EMAIL env var in single-useGitHub Copilot
  • 252487fd on GitHubApply suggestions from code reviewGitHub Copilot
  • 1a1e6487 on GitHubPotential fix for code scanning alert no. 51: Workflow does not contain peGitHub 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 window1,742
Merge commits removed−529
CI / dependency bots removed−71
Considered1,142

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 →Python AI coding statisticsCompare evidence across Python 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 taylorwilsdon/google_workspace_mcp

Scan another repository

Try