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.

Install an OpenShift 4.x cluster

01Result

openshift/installer ↗

openshift/installer AI coding statistics: 11.9%

of 437 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
11.9% agent · top contributor 9.6%26 contributors
org-wide

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

52
agent commits
385
other considered commits
26
agent contributors
9.6%
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

52assisted
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
2026-025.1%39
2026-031%105
2026-0416.3%43
2026-0520%35
2026-0614.1%71
2026-0716.9%59
2026-0818.1%72
2026-0915.4%13

Peak month: 20%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic429.6%
Cursor AgentAnysphere51.1%
GitHub CopilotGitHub30.7%
OpenAI CodexOpenAI20.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • a0e52b43 on GitHubmulti-disk: fix swap disk nil-panic and block swap on control planeClaude Code
  • 9a4611f5 on GitHubOCPBUGS-59743: azure: reject data disks on Azure Stack HubClaude Code
  • 7875723d on GitHubOCPBUGS-114375: azure: skip AppendVarPartition when DiskSetup claims /varClaude Code
  • a4e4b4a8 on GitHubOCPBUGS-88511: Disable apps DNS validation for add-nodesCursor Agent
  • f7975795 on GitHubAzure: delete bootstrap ignition storage during bootstrap destroyCursor Agent
  • 89a316fb on GitHubOCPBUGS-86311: fix: validate agent-config interface names match networkConCursor Agent
  • e34a064c on GitHubazure: use capacity reservations for CAPI control planeGitHub Copilot
  • 2b0cf20f on GitHubunit tests: cover Azure reservation group name boundariesGitHub Copilot
  • 5c8d9f9d on GitHubazure: validate capacity reservation groupsGitHub Copilot
  • 376997a8 on GitHubBaremetal: use only the primary ip when gathering info from mastersOpenAI Codex
  • 6c294eb6 on GitHubinstaller gather: add a timeout to ssh / scpOpenAI 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 window687
Merge commits removed−250
CI / dependency bots removed−0
Considered437

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Go AI coding statisticsCompare evidence across Go 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 openshift/installer

Scan another repository

Try