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.

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

01Result

mikeyobrien/ralph-orchestrator ↗

mikeyobrien/ralph-orchestrator AI coding statistics: 21.2%

of 170 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

21.2% agent · top contributor 27.8%11 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

agent commits

134

other considered commits

agent contributors

27.8%

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

36assisted

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	29	17.1%
GitHub Copilot	GitHub	5	2.9%
OpenAI Codex	OpenAI	2	1.2%

03Evidence

Inspect the matches

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

Matched commit samples

e2a9d566 on GitHubfeat(doctor): recognize OrcaRouter as a named provider for models.dev backClaude Code
087f908f on GitHubchore: bump to v2.10.0 (#338)Claude Code
317266fb on GitHubfix(tui): capture keystrokes in search input mode (#337)Claude Code
c7c3cf5b on GitHubSupport richer Copilot JSON stream eventsGitHub Copilot
8fdb0c63 on GitHubUse Copilot stream parser namingGitHub Copilot
803c4a6b on GitHubfix(adapters): use inactivity timeout for cli executionGitHub Copilot
78c94d3d on GitHubConsolidate core presets and harden multi-hat orchestration (#236)OpenAI Codex
5b5acda9 on GitHubFix review debug event contractsOpenAI Codex

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	189
Merge commits removed	−19
CI / dependency bots removed	−0
Considered	170

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Rust AI coding statisticsCompare evidence across Rust repositories →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 mikeyobrien/ralph-orchestrator

Scan another repository

Try

Month	Agent share	Considered commits
2026-01	100%	1
2026-02	14.3%	42
2026-03	31.4%	70
2026-04	10%	20
2026-05	16.7%	12
2026-06	11.1%	18
2026-07	0%	4
2026-08	33.3%	3