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.

Conformance test suite for OpenShift

01Result

openshift/origin ↗

openshift/origin AI coding statistics: 20%

of 887 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
20% agent · top contributor 22%43 contributors
org-wide

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

177
agent commits
710
other considered commits
43
agent contributors
22%
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

177assisted
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
2026-0211%91
2026-0322.5%111
2026-0419.2%125
2026-0517.1%129
2026-068.1%173
2026-0740.9%127
2026-0824.4%82
2026-0920.4%49

Peak month: 40.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic15817.8%
Cursor AgentAnysphere242.7%

03Evidence

Inspect the matches

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

Matched commit samples

  • d340df64 on GitHubAdd --extension-binaries flag for local extension binary loadingClaude Code
  • f184c8c0 on GitHubIncrease timeout for external IP policy test to accommodate in-cluster rolClaude Code
  • 4c63d00b on GitHubAdd --skip-readiness-checks flag to e2e-analysis subcommandClaude Code
  • ab68bd18 on GitHubTRT-2830: add REVIEW.md for agentic review responsesCursor Agent
  • 0819c618 on GitHubmonitortests: allow image-registry node-ca Progressing on DualReplicaCursor Agent
  • 638822f1 on GitHubRequire NoExecuteTaintManager overlap for DualReplica Available exceptionsCursor 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 window1,373
Merge commits removed−486
CI / dependency bots removed−0
Considered887

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 →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/origin

Scan another repository

Try