Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

goharbor/harbor ↗

goharbor/harbor AI coding statistics: 5.2%

of 229 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.2% agent · top contributor 50%7 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

12
agent commits
217
other considered commits
7
agent contributors
50%
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

12assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0211.1%18
2026-035.6%18
2026-040%21
2026-053.4%29
2026-060%45
2026-0710.3%29
2026-084.3%47
2026-0913.6%22

Peak month: 13.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub73.1%
Cursor AgentAnysphere62.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • aea94352 on GitHubrefactor(p2p): improve HTTP client request logging and credential string fGitHub Copilot
  • e444bc49 on GitHubfix: avoid panic in user audit event resolver on nil event data (#23461)GitHub Copilot
  • abc41cc9 on GitHubFix/api completeness (#23476)GitHub Copilot
  • 3a949807 on GitHubrefactor: sanitize connection details in logs and enhance error message foCursor Agent
  • aea94352 on GitHubrefactor(p2p): improve HTTP client request logging and credential string fCursor Agent
  • 73cff4d7 on GitHubRemove hardcoded credentials and prevernt passwords in logs (#23835)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 window260
Merge commits removed−0
CI / dependency bots removed−31
Considered229

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
goharbor/harbor
Default branch
main
Resolved HEAD
eadf89a5fb351b3d9390956877294ba6f5123342 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortGo · 132 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 62 of 194 ecosystem repositories excluded
Agent-commit share position64th percentile

Midrank percentile; equal shares split the tied positions.

Repository
5.2%
Cohort median
2.8%
Share rank
48 / 132
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 132.

Continue exploring

GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →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 goharbor/harbor

Scan another repository

Try