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.

Build and deploy AI Agents on Cloudflare

01Result

cloudflare/agents ↗

cloudflare/agents AI coding statistics: 16.9%

of 741 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
16.9% agent · top contributor 79.2%12 contributors
team

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

125
agent commits
616
other considered commits
12
agent contributors
79.2%
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

125assisted
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
2026-0211.8%127
2026-031.6%126
2026-040%132
2026-0552.4%82
2026-0647.7%130
2026-073.7%54
2026-081.8%57
2026-090%33

Peak month: 52.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere11615.7%
DevinCognition81.1%
Claude CodeAnthropic60.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • 62b90eba on GitHubfix(think): preserve attachment fetchMetadata through messenger serializatCursor Agent
  • cc21f094 on GitHubfix(chat): serialize reconnect-driven resumes to stop activeResponse race Cursor Agent
  • 0544aa2c on GitHubfix(agent-tools): clone run parts in reducer so StrictMode does not doubleCursor Agent
  • fe82e052 on GitHubAdd Kitesurf support to Browser Tools (#2098)Devin
  • cb4c1c72 on GitHubfeat: update AI SDK to v7 (#1922)Devin
  • ed9f42b4 on GitHubfix(think): forward props through onStart wrapper (#1937)Devin
  • 99c9326b on GitHubfix(agents): defer agent teardown to its own alarm invocation so canceled Claude Code
  • c18a446d on GitHubfix: stop oversized sessions from bricking the DO with SQLITE_NOMEM on wakClaude Code
  • bc431338 on GitHubfix(agents,ai-chat,think): replay errored-stream content and scope agent-tClaude Code

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 window866
Merge commits removed−2
CI / dependency bots removed−123
Considered741

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin 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 cloudflare/agents

Scan another repository

Try