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.

Primary repository for the Trilinos Project

01Result

trilinos/Trilinos ↗

trilinos/Trilinos AI coding statistics: 3.8%

of 1,031 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.8% agent · top contributor 82.1%5 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

39
agent commits
992
other considered commits
5
agent contributors
82.1%
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

37assisted
2autonomous

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
2026-021.6%129
2026-030%87
2026-040%158
2026-050%123
2026-063.8%105
2026-071.6%128
2026-084.9%205
2026-0921.9%96

Peak month: 21.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic373.6%
GitHub CopilotGitHub20.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • eeae9b47 on GitHubPanzer: use Tpetra host views in the Dirichlet scatterClaude Code
  • 88036eb9 on GitHubPanzer: cache temporaries in the scattersClaude Code
  • bb0fc2e1 on GitHubPanzer: support non-square blocked Tpetra linear object factoriesClaude Code
  • 97d77598 on GitHubComplete test_02.hpp relative error updates for all remaining filesGitHub Copilot
  • 3c615a19 on GitHubUpdate test_02.hpp files: convert to relative error (HCURL, HDIV, partial GitHub 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 window1,515
Merge commits removed−458
CI / dependency bots removed−26
Considered1,031

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 →C++ AI coding statisticsCompare evidence across C++ 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 trilinos/Trilinos

Scan another repository

Try