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.

Free, open-source tiling window manager for Apple Silicon Macs, with Niri-style scrolling containers and Hyprland-style Dwindle BSP.

01Result

OmniNull/OmniWM ↗

OmniNull/OmniWM AI coding statistics: 4.2%

of 966 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4.2% agent · top contributor 41.5%9 contributors
org-wide

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

41
agent commits
925
other considered commits
9
agent contributors
41.5%
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

41assisted
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
2026-021.8%57
2026-0311.9%160
2026-040%23
2026-051.9%104
2026-060%169
2026-073.1%131
2026-081.9%161
2026-097.5%161

Peak month: 11.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic373.8%
GitHub CopilotGitHub20.2%
OpenAI CodexOpenAI20.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 6547bd24 on GitHubKeep only the installed dev copy registered with LaunchServicesClaude Code
  • f0cb74c1 on GitHubAddress review: no name fallback for UUID entries, label roles by connecteClaude Code
  • db0d9797 on GitHubAdd a monitor ranking that decides the Main, Secondary, and Tertiary rolesClaude Code
  • 9064f502 on GitHubAddress review: drop redundant session patch, always stop source scrollGitHub Copilot
  • b35d39d4 on GitHubFollow focus on up/down and column moves to workspaceGitHub Copilot
  • ea83a507 on GitHubfix: correct Niri viewport origin for inset working areasOpenAI Codex
  • 0ee5d7a3 on GitHubfix: preserve tiled mode during heuristic reevaluationOpenAI Codex

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 window1,018
Merge commits removed−52
CI / dependency bots removed−0
Considered966

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 OmniNull/OmniWM

Scan another repository

Try