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.

Your Software Factory - build faster and better with multi node agents that work 24/7

01Result

Runfusion/Fusion ↗

Runfusion/Fusion AI coding statistics: 16.9%

of 13,590 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
16.9% agent · top contributor 95%17 contributors
individual

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

2,298
agent commits
11,292
other considered commits
17
agent contributors
95%
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

2292assisted
6autonomous

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
2026-030.1%787
2026-0415.5%2617
2026-059.3%4252
2026-0620.6%2361
2026-0733.6%2566
2026-0815%985
2026-094.5%22

Peak month: 33.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic229016.9%
GitHub CopilotGitHub60%
OpenAI CodexOpenAI20%

03Evidence

Inspect the matches

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

Matched commit samples

  • c8dfb471 on GitHubfix(dashboard): retry the System capability probe until it landsClaude Code
  • 2d12078e on GitHubfix(merge): a landed merge must finalize even when the row has no stepsClaude Code
  • 438cd550 on GitHubfix(remote-access): adopt a live funnel without requiring a running markerClaude Code
  • 8544b5b0 on GitHubfix(FN-7143): simplify base64 validation and improve error messagesGitHub Copilot
  • b0c42974 on GitHubfix(engine): correct parameter order in runVerificationCommand after mergeGitHub Copilot
  • 741fc159 on GitHubtest(FN-66): stabilize remote provider activation assertionGitHub Copilot
  • 8c055a66 on GitHubfix: keep self-healing sweeps alive across stale task links (#3417)OpenAI Codex
  • ccebe5c5 on GitHubfix(engine): keep orphaned planning recovery alive (#3399)OpenAI Codex

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 window14,078
Merge commits removed−452
CI / dependency bots removed−36
Considered13,590

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 Runfusion/Fusion

Scan another repository

Try