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.

🌊 Julia software for fast, friendly, flexible, ocean-flavored fluid dynamics on CPUs and GPUs

01Result

CliMA/Oceananigans.jl ↗

CliMA/Oceananigans.jl AI coding statistics: 35.7%

of 431 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
35.7% agent · top contributor 29.2%15 contributors
org-wide

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

154
agent commits
277
other considered commits
15
agent contributors
29.2%
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

154assisted
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
2026-0216.1%62
2026-0335.5%62
2026-0432.7%49
2026-0529.2%48
2026-0640.7%59
2026-0740.7%54
2026-0836.4%44
2026-0956.6%53

Peak month: 56.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic14834.3%
GitHub CopilotGitHub122.8%
Cursor AgentAnysphere10.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1fe0edef on GitHubFix some issues in test suite (#5998)Claude Code
  • 98e240d9 on GitHubKeep field and output order in FieldDataset and ordered writer inputs (#59Claude Code
  • d95f3645 on GitHubRead dimension lengths from the dataset when showing a NetCDFWriter (#5986Claude Code
  • ebecd841 on GitHubOpen boundary conditions using `SplitExplicitFreeSurface` (#5351)GitHub Copilot
  • e0cf20dc on GitHubImprove docstrings for `viscosity` and `diffusivity` (#5813)GitHub Copilot
  • 03d4d779 on GitHubFix error reading FieldTimeSeries from NetCDF (#5684)GitHub Copilot
  • 1d964955 on GitHubAdd random seeds to examples for reproducible results (#5312)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 window440
Merge commits removed−1
CI / dependency bots removed−8
Considered431

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 →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 CliMA/Oceananigans.jl

Scan another repository

Try