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.

Nostr client for Android

01Result

vitorpamplona/amethyst ↗

vitorpamplona/amethyst AI coding statistics: 79.7%

of 7,447 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

79.7% agent · top contributor 83.7%7 contributors

individual

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

5,932

agent commits

1,515

other considered commits

agent contributors

83.7%

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

5932assisted

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: 90.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	5930	79.6%
GitHub Copilot	GitHub	2	0%

03Evidence

Inspect the matches

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

Matched commit samples

db28e4ec on GitHubtest(qr): measure the phase-0 baseline and commit the corpusClaude Code
57121fdf on GitHubtest(qr): add the phase-0 decode corpus and its device-free baselineClaude Code
c3cecf1e on GitHubfix(qr): correct the bunker message, and pin what the scanner sheet has toClaude Code
03e1c327 on GitHubPotential fix for pull request findingGitHub Copilot
f4d6e3cb on GitHubApply suggestions from code reviewGitHub 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	10,576
Merge commits removed	−2,594
CI / dependency bots removed	−535
Considered	7,447

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 →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 vitorpamplona/amethyst

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	17.2%	128
2026-03	37.8%	976
2026-04	86.6%	1508
2026-05	84.6%	1322
2026-06	88%	1076
2026-07	90.7%	1650
2026-08	85.5%	421
2026-09	85.2%	366