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.

Self-hosted, semantically-connected personal knowledge base

01Result

kenforthewin/atomic ↗

kenforthewin/atomic AI coding statistics: 55.2%

of 817 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
55.2% agent · top contributor 80.7%7 contributors
individual

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

451
agent commits
366
other considered commits
7
agent contributors
80.7%
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

451assisted
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
2026-010%3
2026-0212.5%48
2026-0325.7%136
2026-0444.5%328
2026-0549.2%59
2026-06100%115
2026-0795.2%104
2026-0887.5%24

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic45155.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 88270c60 on GitHubfix: route schema-less requests in the test and bench mocksClaude Code
  • e2b97009 on GitHubfix: extend prompt-only to merge and wiki section opsClaude Code
  • f97d1bf6 on GitHubfix: state the output contract by example, and consolidate the transportClaude 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 window962
Merge commits removed−145
CI / dependency bots removed−0
Considered817

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 →Rust AI coding statisticsCompare evidence across Rust 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 kenforthewin/atomic

Scan another repository

Try