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.

coss.com/ui is the official design system of Cal.com

01Result

cosscom/ui ↗

cosscom/ui AI coding statistics: 19.2%

of 120 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

19.2% agent · top contributor 82.6%4 contributors

individual

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

agent commits

other considered commits

agent contributors

82.6%

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

21assisted

2autonomous

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: 50%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Devin	Cognition	12	10%
Cursor Agent	Anysphere	10	8.3%
Claude Code	Anthropic	1	0.8%

03Evidence

Inspect the matches

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

Matched commit samples

e8ec1536 on GitHubfeat: prototype bookings (#787)Devin
3bc0bdfa on GitHubfeat: add coss-particles skill with full particle index and generator scriDevin
f2852807 on GitHubfeat(calcom): add settings page prototypes & refactor titles to AppHeader Devin
e937becd on GitHubfeat: migrate TanStack Table to v9 (#848)Cursor Agent
705cb737 on GitHubfix(toast): keep anchored toasts above later-opened popovers (#845)Cursor Agent
19620ae8 on GitHubdocs(changelog): combine segmented control entries under August 19 (#838)Cursor Agent
0630457e on GitHubfix(scroll-area): correct transition-shadows typo so the focus ring animatClaude 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	120
Merge commits removed	−0
CI / dependency bots removed	−0
Considered	120

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin 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 cosscom/ui

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	25%	20
2026-03	12.5%	32
2026-04	10.5%	19
2026-05	11.8%	17
2026-06	0%	7
2026-07	30.8%	13
2026-08	50%	8
2026-09	50%	4