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.

Ruby AOT compiler

01Result

matz/spinel ↗

matz/spinel AI coding statistics: 89%

of 6,766 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

89% agent · top contributor 84.9%24 contributors

individual

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

6,022

agent commits

744

other considered commits

agent contributors

84.9%

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

6022assisted

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	5993	88.6%
Cursor Agent	Anysphere	29	0.4%
OpenAI Codex	OpenAI	1	0%
GitHub Copilot	GitHub	1	0%

03Evidence

Inspect the matches

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

Matched commit samples

02b29848 on GitHubThe string major's backstop is aimed at what the major keptClaude Code
16e36faa on GitHubA slab release keeps the chunk its owner is allocating fromClaude Code
f04b62ca on GitHubA regexp match and a gsub with a Hash keep their small scratch on the stacClaude Code
49350627 on GitHubruntime: String#setbyte sizes the receiver NUL-safelyCursor Agent
0e43926f on GitHubcodegen: root the sp_Proc box of an escaping &blk across the callCursor Agent
cdf4efd4 on GitHubcodegen: fix empty print block and nil-string puts on IO constants (reviewCursor Agent
413f6132 on GitHubTreat builtin class reopens as open-class methodsOpenAI Codex
e898e384 on GitHubAvoid leading spaces in EXTRA_FLAGSGitHub 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	7,840
Merge commits removed	−1,074
CI / dependency bots removed	−0
Considered	6,766

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 matz/spinel

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	100%	249
2026-04	84%	443
2026-05	86.1%	1322
2026-06	93.1%	1432
2026-07	87.6%	1757
2026-08	93.2%	1089
2026-09	79.3%	474