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.

A framework for building agentic apps

01Result

BuilderIO/agent-native ↗

BuilderIO/agent-native AI coding statistics: 4.7%

of 4,082 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4.7% agent · top contributor 42%19 contributors
org-wide

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

193
agent commits
3,889
other considered commits
19
agent contributors
42%
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

192assisted
1autonomous

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
2026-037.5%375
2026-046.7%375
2026-053.3%421
2026-065.6%553
2026-077.2%808
2026-082.5%978
2026-092.3%572

Peak month: 7.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1092.7%
Cursor AgentAnysphere822%
GitHub CopilotGitHub20%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8fb9e578 on GitHubfix: regenerate favicon and app icons from monochrome logo (#4787)Claude Code
  • 06a60ecf on GitHubRedesign Slides landing page to match Clips (#4792)Claude Code
  • 68a60c56 on GitHubfix(mail): default to first label, enable global Tab label cycling, and fiClaude Code
  • 0dc7290a on GitHubfix: simplify device authorization screen and use terminal icon (#4680)Cursor Agent
  • 345dc586 on GitHubFactory PR babysitting asks once, then stays quiet until new review feedbaCursor Agent
  • e32b0345 on GitHubFactory jobs use vault tokens, stay usable during outages, and audit runs Cursor Agent
  • ac1b0df9 on GitHubfeat: add support for disabling default plugins and configuring (#3221)GitHub Copilot
  • 15a87743 on GitHubmerge: resolve conflict with origin/main, integrate logo in Sidebar headerGitHub 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 window5,535
Merge commits removed−284
CI / dependency bots removed−1,169
Considered4,082

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 →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 BuilderIO/agent-native

Scan another repository

Try