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.

Static type checker for Ruby

01Result

soutaro/steep ↗

soutaro/steep AI coding statistics: 63.5%

of 167 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

63.5% agent · top contributor 84.9%7 contributors

individual

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

106

agent commits

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

106assisted

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	106	63.5%

03Evidence

Inspect the matches

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

Matched commit samples

77b750d1 on GitHubDrop the LSP lifecycle from the worker protocolClaude Code
47302a3f on GitHubRegenerate the RBS of master_test.rbClaude Code
b91bc861 on GitHubHand out one type check job per worker per roundClaude 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	395
Merge commits removed	−155
CI / dependency bots removed	−73
Considered	167

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 soutaro/steep

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	7
2026-03	0%	18
2026-04	43.1%	58
2026-05	50%	2
2026-06	100%	1
2026-08	94.4%	36
2026-09	100%	45