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.

An acausal modeling framework for automatically parallelized scientific machine learning (SciML) in Julia. A computer algebra system for integrated symbolics for physics-informed machine learning and automated transformations of differential equations

01Result

SciML/ModelingToolkit.jl ↗

SciML/ModelingToolkit.jl AI coding statistics: 22.2%

of 1,110 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
22.2% agent · top contributor 24.8%15 contributors
org-wide

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

246
agent commits
864
other considered commits
15
agent contributors
24.8%
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

246assisted
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
2026-0222.4%174
2026-039.6%104
2026-046.5%107
2026-059.4%138
2026-0617.8%163
2026-0720.1%194
2026-0835.7%171
2026-0981.4%59

Peak month: 81.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic23721.4%
DevinCognition60.5%
Cursor AgentAnysphere50.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • f6a6d324 on GitHubRelease ModelingToolkitBase 1.73.0 (#5156)Claude Code
  • 6e914077 on GitHubCompare `complete` and `mtkcompile` array-unknown problems through symboliClaude Code
  • 9ebc49e0 on GitHubRaise SymbolicIndexingInterface compat lower bound to 0.3.47 (#5153)Claude Code
  • 0ed8046c on GitHubUnify array-equation support behind a capability trait; fold in #5101 ODE Devin
  • 21814d32 on GitHubFix getbounds for scalar bounds on array variables (#5124)Devin
  • 887af5f4 on GitHubAdd constraints_to_penalties: lower constraints to quadratic penalty costsDevin
  • 0ed8046c on GitHubUnify array-equation support behind a capability trait; fold in #5101 ODE Cursor Agent
  • fcda4b8c on GitHubRequire Symbolics 7.39.1 (32-bit hash fix) (#5096)Cursor Agent
  • f9131984 on GitHubSplit Downgrade Sublibraries by MTKBase test group. (#5041)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 window1,532
Merge commits removed−418
CI / dependency bots removed−4
Considered1,110

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 →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 SciML/ModelingToolkit.jl

Scan another repository

Try