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.

Secure, open source and community driven crypto wallet runs on all platforms and trusted by millions.

01Result

OneKeyHQ/app-monorepo ↗

OneKeyHQ/app-monorepo AI coding statistics: 5.7%

of 2,550 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.7% agent · top contributor 30.1%23 contributors
org-wide

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

146
agent commits
2,404
other considered commits
23
agent contributors
30.1%
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

145assisted
1autonomous

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
2026-027.1%394
2026-0312.7%411
2026-041.7%349
2026-055.2%287
2026-062.8%283
2026-074.4%317
2026-083.1%193
2026-095.4%316

Peak month: 12.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic773%
DevinCognition451.8%
Cursor AgentAnysphere361.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7da1c68c on GitHubchore: bump hardware SDK to 1.2.2-alpha.119 (#13361)Claude Code
  • 25aec101 on GitHubfix: make lock screen Forgot passcode usable on extension and iOS (OK-6241Claude Code
  • c6f67e99 on GitHubfix: stop settings modal flashing back to loading OK-53013 (#13367)Claude Code
  • 42ed74b7 on GitHubfeat(desktop): add macOS menu bar tray with wallet overview and watchlist Devin
  • 3cfdc1f3 on GitHubfeat: add prime auth token to check-host request for Blockaid integration Devin
  • 196ac457 on GitHubchore: sync release/v6.1.0 to x (#10904)Devin
  • 8f00ab36 on GitHubfix: k-line y-axis compact prices and home stocks API (OK-61836 OK-63335) Cursor Agent
  • 506c7eac on GitHubfix: keep market banner tokens stable during list refresh ｜OK-63137 (#1343Cursor Agent
  • 4f45ff37 on GitHubfix: handle Discovery IME Enter confirmation OK-62394 (#13254)Cursor Agent

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 window2,552
Merge commits removed−0
CI / dependency bots removed−2
Considered2,550

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 OneKeyHQ/app-monorepo

Scan another repository

Try