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 design system studio for humans and agents.

01Result

mehdibha/dotUI ↗

mehdibha/dotUI AI coding statistics: 28.7%

of 390 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
28.7% agent · top contributor 87.5%2 contributors
individual

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

112
agent commits
278
other considered commits
2
agent contributors
87.5%
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

112assisted
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
2026-03100%2
2026-0560%5
2026-0680%120
2026-074.5%132
2026-080%73
2026-098.6%58

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic10226.2%
Cursor AgentAnysphere102.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • eee4536c on GitHubfeat(www): rework hero for mobile, copy, and stack logos (#716)Claude Code
  • 49f4a0f7 on GitHubfeat(registry): ship semantic tokens as literals, drop the ramps from expoClaude Code
  • 041041cc on GitHubci(examples): verify templates on PRs, commit them with the change (#714)Claude Code
  • 5d89bf51 on GitHubdocs: replace gallery mode toggle with a preset intro (#742)Cursor Agent
  • 9e548873 on GitHubfix(docs): restore Getting started sidebar section (#741)Cursor Agent
  • 08729d22 on GitHubfix(www): match home skeleton rail gap to cards grid (#473)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 window391
Merge commits removed−0
CI / dependency bots removed−1
Considered390

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 →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 mehdibha/dotUI

Scan another repository

Try