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.

Open Source Graphical Programming for Computational Design and Automation

01Result

DynamoDS/Dynamo ↗

DynamoDS/Dynamo AI coding statistics: 40.3%

of 226 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
40.3% agent · top contributor 19.8%17 contributors
org-wide

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

91
agent commits
135
other considered commits
17
agent contributors
19.8%
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

91assisted
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
2026-0245.5%33
2026-0323.3%43
2026-0441.7%36
2026-0533.3%15
2026-0651.6%31
2026-0760.7%28
2026-0836.7%30
2026-0920%10

Peak month: 60.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic5524.3%
GitHub CopilotGitHub3816.8%
Cursor AgentAnysphere41.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • 16e32e2c on GitHubDYN-10801: Fix Custom Selection node losing items after delete + undo (#17Claude Code
  • e840b894 on GitHubDYN-10818: Bump DynamoMCP to 0.5.9 (#17319)Claude Code
  • c63f4c5a on GitHubDYN-10569: Only warn on Python port removal when the port has custom propeClaude Code
  • 80eee146 on GitHubDYN-10736 Dynamo Player sample file incorrectly appears under Revit sampleGitHub Copilot
  • 1f3b3d51 on GitHubDYN-10705: Add DynamoMCP OSS attributions to ABOUT.txt (#17228)GitHub Copilot
  • 31b73b87 on GitHubDYN-10642 Enforce no-network startup behavior for WebView2 surfaces (#1721GitHub Copilot
  • 2deb3b59 on GitHubDYN-9078: Node context menu chevron doesn't change color on hover (#17124)Cursor Agent
  • 6987df3b on GitHubDYN-9724: Allow Pins to Stay Until Connector is Actually Disconnected (#16Cursor Agent
  • de6a26b1 on GitHubDYN-7301, DYN-9908: Update LibG NuGet packages for ASM 231 and 232 to lateCursor 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 window238
Merge commits removed−0
CI / dependency bots removed−12
Considered226

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 DynamoDS/Dynamo

Scan another repository

Try