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.

⛅️ Home to Wrangler, the CLI for Cloudflare Workers®

cloudflare/workers-sdk ↗

cloudflare/workers-sdk AI coding statistics: 8.6%

of 1,438 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
8.6% agent · top contributor 19.4%50 contributors
org-wide

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

124
agent commits
1,314
other considered commits
50
agent contributors
19.4%
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

120assisted
4autonomous

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
2026-028.2%195
2026-0310%219
2026-0411.7%205
2026-057.4%176
2026-067.5%186
2026-079.9%192
2026-085.8%155
2026-096.4%110

Peak month: 11.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
DevinCognition986.8%
Claude CodeAnthropic221.5%
GitHub CopilotGitHub40.3%
Cursor AgentAnysphere20.1%
Other / generic agentVarious10.1%

Inspect the matches

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

Matched commit samples

  • ca71205b on GitHubRemove Web Search binding and commands (#15453)Devin
  • a0856da6 on GitHub[wrangler] Preserve serialized error details in castErrorCause (#14906)Devin
  • b605aa60 on GitHub[wrangler] Correct Pages delegation analytics (#15581)Devin
  • dbb3ff4e on GitHub[miniflare] Fix DevalueError when passing cross-realm Headers to proxied bClaude Code
  • a4e41df4 on GitHub[wrangler] Fix wrangler dev running the custom build command twice (#15542Claude Code
  • 682cd44f on GitHubfix(wrangler): keep `wrangler dev` alive when a proxied request to the UseClaude Code
  • ad8d4b24 on GitHub[local-explorer-ui] Fix data studio cell keydown swallowing browser shortcGitHub Copilot
  • b8439fbb on GitHub[miniflare][wrangler] Fix Windows CI flakes: local-explorer ECONNRESET retGitHub Copilot
  • 92bb8a52 on GitHubwrangler types --check` fails with `Invalid value: true (#13695)GitHub Copilot
  • cb0955f2 on GitHubTreat 502/503/504 as gateway errors during asset upload retries (#15179)Cursor Agent
  • 2cb658c8 on GitHub[vitest-pool-workers] Preserve wrapped RPC call ordering (#13961)Cursor Agent
  • 17d2fc12 on GitHub[wrangler] Add `turnstile widget` CLI commands (#14511)Other / generic agent

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 window1,726
Merge commits removed−0
CI / dependency bots removed−288
Considered1,438

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 cloudflare/workers-sdk

Scan another repository