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.

01Result

vortexgpgpu/vortex ↗

vortexgpgpu/vortex AI coding statistics: 48.7%

of 2,168 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

48.7% agent · top contributor 95.5%9 contributors

individual

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

1,055

agent commits

1,113

other considered commits

agent contributors

95.5%

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

1055assisted

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: 96.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1055	48.7%

03Evidence

Inspect the matches

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

Matched commit samples

1cd71c40 on GitHubFix barrier phase routing and global response tracking (#407)Claude Code
bf1831ca on GitHubtests/unittest: cover reserved RVC code pointsClaude Code
88d692cc on GitHubsimx: align the RV32 shamt[5] guards with the ifdef indent conventionClaude 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 window	2,278
Merge commits removed	−110
CI / dependency bots removed	−0
Considered	2,168

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 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 vortexgpgpu/vortex

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	3.2%	95
2026-03	12%	166
2026-04	15.3%	150
2026-05	26.5%	869
2026-06	84.8%	302
2026-07	83.5%	315
2026-08	96.2%	261
2026-09	90%	10