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.

The missing open-source Kubernetes UI with a built-in MCP server for AI agents. See what's broken, why, and what changed. Issues, Topology, event timeline, Helm, GitOps, live service traffic, and cluster audits - all in one Go binary.

01Result

skyhook-io/radar ↗

skyhook-io/radar AI coding statistics: 7.5%

of 1,098 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
7.5% agent · top contributor 28%18 contributors
org-wide

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

82
agent commits
1,016
other considered commits
18
agent contributors
28%
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

82assisted
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
2026-0225.4%122
2026-032.6%78
2026-040%170
2026-057%157
2026-061.5%134
2026-072.2%135
2026-084.8%165
2026-0918.2%137

Peak month: 25.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic706.4%
Cursor AgentAnysphere100.9%
GitHub CopilotGitHub20.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • add16787 on GitHubstyle(rollouts): use the shared Badge/health-tone system instead of ad-hocClaude Code
  • 04f8a935 on GitHubfix(rollouts): guard the Experiment renderer against Katib's same-plural CClaude Code
  • 33b53cc5 on GitHubfix(rollouts): correct Argo Rollouts analysis-template schema; fix blueGreClaude Code
  • 8e532b98 on GitHubRecognize cert-manager Secrets in the unused-resource audit (#1710)Cursor Agent
  • c0f3cbb9 on GitHubperf(sse): run topology broadcasts on a dedicated worker (#1440)Cursor Agent
  • 9e6d5445 on GitHubfix(desktop): keep window title in sync with cluster context switches (#60Cursor Agent
  • b9dfd843 on GitHubShow in-cluster Radar upgrade status (#1573)GitHub Copilot
  • 9fd32573 on GitHubFix ANSI blocks in logs viewer (#226)GitHub 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 window1,256
Merge commits removed−74
CI / dependency bots removed−84
Considered1,098

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 skyhook-io/radar

Scan another repository

Try