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.

Copy any UI element for your agent

01Result

aidenybai/react-grab ↗

aidenybai/react-grab AI coding statistics: 11.4%

of 615 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

11.4% agent · top contributor 88.6%3 contributors

individual

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

agent commits

545

other considered commits

agent contributors

88.6%

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

67assisted

3autonomous

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: 20.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	56	9.1%
Claude Code	Anthropic	11	1.8%
Devin	Cognition	3	0.5%

03Evidence

Inspect the matches

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

Matched commit samples

38d49956 on GitHubchore: bump bippy to 0.7.2 (#626)Cursor Agent
81d95cca on GitHubRevert keyboard prompt changes from mainCursor Agent
26647d1e on GitHubSkip Next project during coverage runsCursor Agent
4ece9dbd on GitHubchore: rename registry package to shadcn-registryClaude Code
633c5f2a on GitHubchore: remove tailwind-merge dependency (#254)Claude Code
febad9dd on GitHubRefactor: Extract modules from core/index.tsx, eliminate silent error swalClaude Code
95dd8061 on GitHubfix: zero-viewport canvas crash (#495) + fiber-ancestor fallback when owneDevin
d144708b on GitHubperf: extensive perf harness (CPU profiles, deopts, memory, FPS) + skip thDevin
77b974da on GitHubsecurity: harden GitHub Actions against Shai-Hulud supply chain attacks (#Devin

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	630
Merge commits removed	−0
CI / dependency bots removed	−15
Considered	615

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 aidenybai/react-grab

Scan another repository

Try

Month	Agent share	Considered commits
2026-01	0%	6
2026-02	16.1%	180
2026-03	11.1%	126
2026-04	3.4%	89
2026-05	15.3%	98
2026-06	20.7%	29
2026-07	2.6%	77
2026-08	10%	10