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.

AI-first knowledge base and startup OS

01Result

cabinetai/cabinet ↗

cabinetai/cabinet AI coding statistics: 4.6%

of 1,196 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

4.6% agent · top contributor 32.7%9 contributors

org-wide

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

agent commits

1,141

other considered commits

agent contributors

32.7%

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

55assisted

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: 20.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	55	4.6%

03Evidence

Inspect the matches

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

Matched commit samples

18d00509 on GitHubfeat: surface integrations across home, sidebar, and mobile navClaude Code
468993db on GitHubdocs: add root CLAUDE.md orienting agents to the three-process splitClaude Code
0111e7f2 on GitHubtest(e2e): scripted+recording fake agent CLI, 1→16 agent coverage testsClaude 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	1,309
Merge commits removed	−113
CI / dependency bots removed	−0
Considered	1,196

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 cabinetai/cabinet

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	0%	16
2026-04	2.5%	716
2026-05	0.5%	195
2026-06	7.8%	153
2026-07	20.9%	115
2026-08	0%	1