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 Art World in Your Pocket or Your Trendy Tech Company's Tote, Artsy's mobile app.

01Result

artsy/eigen ↗

artsy/eigen AI coding statistics: 15%

of 653 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
15% agent · top contributor 31.6%13 contributors
org-wide

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

98
agent commits
555
other considered commits
13
agent contributors
31.6%
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

98assisted
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
2026-024.4%68
2026-039%100
2026-045.2%58
2026-053.1%65
2026-0620.3%79
2026-0734.7%124
2026-0820%100
2026-093.4%59

Peak month: 34.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic9013.8%
Cursor AgentAnysphere40.6%
GitHub CopilotGitHub40.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 27fc6da5 on GitHubfeat(art-assistant): sparkles icon (#14055)Claude Code
  • 369cedd3 on GitHubrefactor(DI-453): deprecate onboarding quiz (#14036)Claude Code
  • e04fca01 on GitHubfeat(PHIRE-3402): tag Sentry events with the current route and open bottomClaude Code
  • 124bb52f on GitHubfeat(city): show an artwork rail on each event card (#13971)Cursor Agent
  • 9d19615d on GitHubperf: lazily render inactive tabs in Inbox and City guide (#13972)Cursor Agent
  • 4b59cfd8 on GitHubrefactor(city): extract shared City/Map types to app/utils (#13962)Cursor Agent
  • 0967d603 on GitHubfeat(ONYX-2170): nwfy rail live refresh (#13787)GitHub Copilot
  • f99160f0 on GitHubchore: remove discarded onyx_auctions_hub experiment flag (ONYX-2090) (#13GitHub Copilot
  • f7f3ca6b on GitHubchore(unleash): remove onyx_artwork-card-save-and-follow-cta-redesign flagGitHub Copilot

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 window787
Merge commits removed−9
CI / dependency bots removed−125
Considered653

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 →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 artsy/eigen

Scan another repository

Try