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
moeru-ai/airi ↗

moeru-ai/airi AI coding statistics: 1.3%

of 1,771 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.3% agent · top contributor 17.4%18 contributors
org-wide

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

23
agent commits
1,748
other considered commits
18
agent contributors
17.4%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

23assisted
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
2026-020.4%276
2026-031.4%510
2026-043.5%283
2026-050%179
2026-060%108
2026-070%115
2026-081.3%223
2026-092.6%77

Peak month: 3.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Gemini CLIGoogle100.6%
Claude CodeAnthropic70.4%
Cursor AgentAnysphere50.3%
GitHub CopilotGitHub20.1%

Inspect the matches

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

Matched commit samples

  • 4ba5b13c on GitHubfix(stage-ui): correct stream reuse when switching sources + improve captuGemini CLI
  • 0976c53d on GitHubchore(ci): modified CI for Godot stage (#1716)Gemini CLI
  • 567fd666 on GitHubfeat(stage-tamagotchi-godot): initiation of Godot stage (#1697)Gemini CLI
  • 5f3746ea on GitHubfix(stage-tamagotchi): grant screen capture through the media permission (Claude Code
  • 0c3655ee on GitHubrefactor(inference): replace custom AsyncMutex with async-mutex package (#Claude Code
  • 147d077a on GitHubfeat(inference): unify and optimize WebGPU inference pipeline (#1622)Claude Code
  • 37c837e5 on GitHubrefactor(api): extract payment CORE to support other payment providers [1/Cursor Agent
  • 9a76eaec on GitHubfix(server): trust moeru-ai Cloudflare Workers preview origins (#2513)Cursor Agent
  • fd8b7a0a on GitHubfeat(core-agent): bump xsai / remove patches (#2164)Cursor Agent
  • d85709f9 on GitHubfeat(stage-ui): webgpu detect improved (#1681)GitHub Copilot
  • 92e75d86 on GitHubfeat(stage-tamagotchi): add electron main process file logger hook (#1247)GitHub Copilot

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 window1,932
Merge commits removed−3
CI / dependency bots removed−158
Considered1,771

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

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
moeru-ai/airi
Default branch
main
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

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.

CohortJS/TS · 376 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 194 of 570 ecosystem repositories excluded
Agent-commit share position27th percentile

Midrank percentile; equal shares split the tied positions.

Repository
1.3%
Cohort median
5.4%
Share rank
274 / 376
0th50th100th

Percentile = (repositories below + half of 5 tied repositories) ÷ 376.

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 moeru-ai/airi

Scan another repository