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.

Mobile web browser providing access to websites that use the Ethereum blockchain

01Result

MetaMask/metamask-mobile ↗

MetaMask/metamask-mobile AI coding statistics: 19.9%

of 7,380 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
19.9% agent · top contributor 6.1%121 contributors
org-wide

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

1,465
agent commits
5,915
other considered commits
121
agent contributors
6.1%
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

1312assisted
153autonomous

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%834
2026-036.3%960
2026-047.8%943
2026-0516.4%933
2026-0619.9%1200
2026-0731%1143
2026-0834.6%884
2026-0937.5%483

Peak month: 37.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere117515.9%
Claude CodeAnthropic2944%
GitHub CopilotGitHub380.5%
DevinCognition80.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 60afd11d on GitHubfix: update AvatarNetwork XS radius (#36289)Cursor Agent
  • cc178692 on GitHubtest(appium): stabilize two-leg swap-action smoke after bridge-back fix (#Cursor Agent
  • 161d8a36 on GitHubfeat: use featureId to enable/disable SwapQuotesProvider (#36106)Cursor Agent
  • d1fe161d on GitHubci: collapse appium smoke test suites into dynamic matrix (MCWP-740) (#361Claude Code
  • 8ad5dff6 on GitHubfeat(perf): Hermes CPU profiling for performance APKs without React NativeClaude Code
  • a8badc54 on GitHubtest(cv): expand Perps CV coverage and replace perps-position E2E (#36119)Claude Code
  • a096b0c0 on GitHubfeat: DeFi virtualized list (#36258)GitHub Copilot
  • 20a22ace on GitHubtest(appium): mock money positions and arb1 RPC for approve cleanup (#3597GitHub Copilot
  • 2a05fb22 on GitHubchore(ci): remove Bitrise Build Hub shadow plumbing (INFRA-3844) (#35354)GitHub Copilot
  • 90ec6b32 on GitHubCherry-picking commits from main to release/8.11.0 for PR #35996 (#36012)Devin
  • 3cc6c3e1 on GitHubchore(runway): cherry-pick fix: perps orderbook tap price precision (#3511Devin
  • fb417276 on GitHubchore(runway): cherry-pick feat: track notification_template_variant on soDevin

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 window8,522
Merge commits removed−359
CI / dependency bots removed−783
Considered7,380

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 →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 MetaMask/metamask-mobile

Scan another repository

Try