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.

Library packaging and distribution for Ruby.

01Result

ruby/rubygems ↗

ruby/rubygems AI coding statistics: 61.6%

of 994 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

61.6% agent · top contributor 90%14 contributors

individual

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

612

agent commits

382

other considered commits

agent contributors

90%

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

600assisted

12autonomous

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: 79.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	599	60.3%
GitHub Copilot	GitHub	14	1.4%

03Evidence

Inspect the matches

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

Matched commit samples

41ad901a on GitHubLook up bundler-<command> executables only in PATHClaude Code
65b695c6 on GitHubSupport safe.bareRepository=explicit in git sourcesClaude Code
4467791d on GitHubBuild a platform gem with gem build --platform for the local platformClaude Code
fc231062 on GitHubPotential fix for pull request findingGitHub Copilot
40112f76 on GitHubSkip bundler self-checksum on ruby-core in test fixtures (#9506)GitHub Copilot
951ef62f on GitHubUse distinct gemspec filenames in stub_with_version and stub_without_versiGitHub 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	1,424
Merge commits removed	−381
CI / dependency bots removed	−49
Considered	994

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 ruby/rubygems

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	4.4%	45
2026-03	40.4%	171
2026-04	69.7%	66
2026-05	55.8%	129
2026-06	71.4%	213
2026-07	63.2%	95
2026-08	79.2%	154
2026-09	73.6%	121