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.

Dynamic Island for macOS

01Result

Ebullioscopic/Atoll ↗

Ebullioscopic/Atoll AI coding statistics: 21.6%

of 784 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
21.6% agent · top contributor 71.6%14 contributors
team

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

169
agent commits
615
other considered commits
14
agent contributors
71.6%
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

164assisted
5autonomous

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
2026-020%49
2026-031.9%103
2026-0412.5%48
2026-055%40
2026-062.6%38
2026-072.9%140
2026-0845.6%327
2026-0912.8%39

Peak month: 45.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic16020.4%
GitHub CopilotGitHub81%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 5b2a2e60 on GitHubfix: choose lyrics that have timings over lyrics that merely match betterClaude Code
  • ff596456 on GitHubfix: show untimed lyrics as lines instead of one enormous lineClaude Code
  • 7beea80b on GitHubfix: actually tint the active glyph, and drop the shortcut with the featurClaude Code
  • 1eee2eb0 on GitHubPotential fix for pull request findingGitHub Copilot
  • 370a4901 on GitHubExtract shared model validation helper in model selection panelGitHub Copilot
  • 2d1f5462 on GitHubDeduplicate OpenAI and Groq response parsing switch casesGitHub Copilot
  • ca48d761 on GitHubFix screen recording HUD stop button while hovering.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 window1,198
Merge commits removed−368
CI / dependency bots removed−46
Considered784

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 →Swift AI coding statisticsCompare evidence across Swift 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 Ebullioscopic/Atoll

Scan another repository

Try