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.

Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

01Result

a5c-ai/babysitter ↗

a5c-ai/babysitter AI coding statistics: 60.2%

of 4,107 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

60.2% agent · top contributor 88.8%24 contributors

individual

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

2,473

agent commits

1,634

other considered commits

agent contributors

88.8%

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

2462assisted

11autonomous

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: 84.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	2458	59.8%
OpenAI Codex	OpenAI	8	0.2%
GitHub Copilot	GitHub	7	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

831eb915 on GitHubcontrib(mathematics): add proof quality convergenceClaude Code
223b55e1 on GitHubfix(observer-dashboard): next 16.3.0, webpack build pin, lockfile regen (cClaude Code
f3731924 on GitHubfix(live-stack): resolve adapters/adapters-hooks bin collision in publisheClaude Code
6c9c7223 on GitHubfeat: Atlas catalog unification (#850)OpenAI Codex
478a2a15 on GitHubfix(sdk): route external agent effects during iteration (#787)OpenAI Codex
a44f5b15 on GitHubfeat: typed ctx.halt lifecycle (#701)OpenAI Codex
44a5d58b on GitHubFix observe command failing to load: quote argument-hint value (#1123)GitHub Copilot
15c01188 on GitHubPotential fix for pull request findingGitHub Copilot
f3004c75 on GitHubPotential fix for pull request findingGitHub 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	5,368
Merge commits removed	−305
CI / dependency bots removed	−956
Considered	4,107

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 →JavaScript AI coding statisticsCompare evidence across JavaScript 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 a5c-ai/babysitter

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	67.1%	140
2026-03	31.4%	220
2026-04	26.1%	967
2026-05	75.7%	1836
2026-06	84.8%	666
2026-07	43.5%	223
2026-08	10.9%	55