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.

HTML is the new markdown. Lavish is the new editor for your HTML artifacts.

01Result

kunchenguid/lavish-axi ↗

kunchenguid/lavish-axi AI coding statistics: 12.1%

of 140 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

12.1% agent · top contributor 41.2%9 contributors

org-wide

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

agent commits

123

other considered commits

agent contributors

41.2%

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

17assisted

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

Peak month: 21.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	9	6.4%
Cursor Agent	Anysphere	7	5%
GitHub Copilot	GitHub	1	0.7%

03Evidence

Inspect the matches

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

Matched commit samples

11825ffc on GitHubchore(deps): harden pnpm trust policy (#278)Claude Code
c229ef49 on GitHubfix(server): reject trailing garbage after a bracketed IPv6 HostClaude Code
879794ad on GitHubfeat(server): support non-loopback hosts and reverse proxiesClaude Code
21737a63 on GitHubfeat: teach diagrams from zero, one concept at a time (#290)Cursor Agent
f658fb83 on GitHubfix: keep the shipped skill as a minimal CLI-deferring stub (#286)Cursor Agent
c62b5f96 on GitHubfix: let artifact popups escape the iframe sandbox (#258)Cursor Agent
0b3e28ea on GitHubfeat(cli): add GitHub Copilot CLI session start hook support (#106)GitHub Copilot

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 window	208
Merge commits removed	−0
CI / dependency bots removed	−68
Considered	140

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 →JavaScript AI coding statisticsCompare evidence across JavaScript 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 kunchenguid/lavish-axi

Scan another repository

Try

Month	Agent share	Considered commits
2026-05	0%	33
2026-06	8.6%	35
2026-07	20%	30
2026-08	21.6%	37
2026-09	0%	5