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

square/leakcanary ↗

square/leakcanary AI coding statistics: 64.8%

of 403 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
64.8% agent · top contributor 97.7%2 contributors
individual

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

261
agent commits
142
other considered commits
2
agent contributors
97.7%
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

261assisted
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
2026-0262.5%24
2026-0333.3%3
2026-050%1
2026-0617.6%51
2026-0773.3%195
2026-0872.1%129

Peak month: 73.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic26164.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • e6728017 on GitHubLog every message an agent sends, and which way in it cameClaude Code
  • b74ce5b5 on GitHubOpen a call from under its row, and keep the tool's name in what it sentClaude Code
  • 9081eb84 on GitHubKeep what an agent sent and read back, and unfold a call onto itClaude Code

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 window529
Merge commits removed−126
CI / dependency bots removed−0
Considered403

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
square/leakcanary
Default branch
main
Resolved HEAD
66aab8d2ab695c4e1c013ed1bd5c3884939c1e2f ↗
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.

CohortJava/Kotlin · 67 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 34 of 101 ecosystem repositories excluded
Agent-commit share position98th percentile

Midrank percentile; equal shares split the tied positions.

Repository
64.8%
Cohort median
0.9%
Share rank
2 / 67
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 67.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code 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 square/leakcanary

Scan another repository

Try