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.

The JavaScript and API powered WordPress.com

Automattic/wp-calypso ↗

Automattic/wp-calypso AI coding statistics: 32.4%

of 4,443 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
32.4% agent · top contributor 11.2%125 contributors
org-wide

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

1,438
agent commits
3,005
other considered commits
125
agent contributors
11.2%
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

1423assisted
15autonomous

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
2026-0210.8%408
2026-0321.9%581
2026-0427.5%422
2026-0526.2%672
2026-0638.3%653
2026-0744%827
2026-0841.3%560
2026-0940.6%320

Peak month: 44%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic138231.1%
GitHub CopilotGitHub611.4%
Cursor AgentAnysphere250.6%
OpenAI CodexOpenAI30.1%

Inspect the matches

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

Matched commit samples

  • 3754a88d on GitHubEmails: downgrade Titan instantly during a free trial (#114368)Claude Code
  • 62c22648 on GitHubDomains: show the pending primary domain notice from the backend field (#1Claude Code
  • d11dd1af on GitHubAgents Manager: Record Tracks for wp-admin navigation (#114310)Claude Code
  • 8e9ce02b on GitHubHelp Center: remember article ratings on the server (#114081)GitHub Copilot
  • 7a40bbc7 on GitHubStats: invite eligible sites to the new Traffic page from classic Stats (#GitHub Copilot
  • 884db620 on GitHubA4A migrations: deep-link marketplace buttons to correct hosting pages (#1GitHub Copilot
  • 36507978 on GitHubRemove completed migration survey (#113633)Cursor Agent
  • 8d3115b2 on GitHubFreshly Pressed Stream - Add badge with Freshly Pressed date (#113478)Cursor Agent
  • 708c10c8 on GitHubFix logged-in Odie chats dropping server-remapped chat ids. (#113274)Cursor Agent
  • 296993c0 on GitHubDesktop: Switch releases to Buildkite (#112079)OpenAI Codex
  • d43d075a on GitHubDesktop: Run e2e tests on Buildkite (#111974)OpenAI Codex
  • 821f8e64 on GitHubDesktop: Build signed Windows NSIS installer on Buildkite (#111455)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 window4,490
Merge commits removed−0
CI / dependency bots removed−47
Considered4,443

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 Automattic/wp-calypso

Scan another repository