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 Bridge between SDN and Cloud Native (Project under CNCF)

01Result

kubeovn/kube-ovn ↗

kubeovn/kube-ovn AI coding statistics: 37%

of 487 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
37% agent · top contributor 94.4%8 contributors
individual

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

180
agent commits
307
other considered commits
8
agent contributors
94.4%
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
3autonomous

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
2026-0248.4%62
2026-0375.2%109
2026-0449.1%53
2026-0541.4%29
2026-0645.1%51
2026-0712.8%39
2026-081%101
2026-092.3%43

Peak month: 75.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic17335.5%
GitHub CopilotGitHub51%
Cursor AgentAnysphere40.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • 250dfda9 on GitHubperf(controller): skip irrelevant service and endpointslice updates (#7037Claude Code
  • 52ebbc10 on GitHubfix: recreate ACLs when ANP/BANP/CNP rule is renamed (#7038)Claude Code
  • cf5e46e2 on GitHubfix: install CNI config and binaries atomically (#7035)Claude Code
  • 86ee7932 on GitHubfeat(veg): add ippool option to vpc egress gateway (#7250)GitHub Copilot
  • 52ebbc10 on GitHubfix: recreate ACLs when ANP/BANP/CNP rule is renamed (#7038)GitHub Copilot
  • 71737cb2 on GitHubfix(ovs): improve dnat_and_snat Add with delete+create for pod swap (#6914GitHub Copilot
  • e6a32a5c on GitHubfeat: add routed subnet mode with /32 addressing and gateway hairpin (#729Cursor Agent
  • 6ef934de on GitHubfix: skip unallocated pods during IPAM initialization to avoid spurious erCursor Agent
  • 7dfd0235 on GitHubrefactor(ovn_leader_checker): improve readability and naming (#6263)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 window780
Merge commits removed−0
CI / dependency bots removed−293
Considered487

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 →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 kubeovn/kube-ovn

Scan another repository

Try