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.

Sanity Studio – Rapidly configure content workspaces powered by structured content

01Result

sanity-io/sanity ↗

sanity-io/sanity AI coding statistics: 30.5%

of 1,208 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

30.5% agent · top contributor 36.7%29 contributors

org-wide

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

368

agent commits

840

other considered commits

agent contributors

36.7%

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

291assisted

77autonomous

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: 55.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	182	15.1%
Claude Code	Anthropic	103	8.5%
GitHub Copilot	GitHub	86	7.1%
OpenAI Codex	OpenAI	1	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

4fe0cb3e on GitHubchore(deps): upgrade react-rx to 7.0.0 (#14643)Cursor Agent
d7d72788 on GitHubchore(deps): upgrade vite (#14700)Cursor Agent
dee6ac74 on GitHubfix(examples): stop importing ui5 in ecommerce studio (#14681)Cursor Agent
9b5a0993 on GitHubfeat(form): make the useFormValue path optional (#14302)Claude Code
15248060 on GitHubchore: untrack the lefthook-generated husky hook (#14060)Claude Code
dbe61d67 on GitHubfeat(releases): instrument release description usage (#13775)Claude Code
8a5c6805 on GitHubchore: migrate flex in dev (#14523)GitHub Copilot
9222afc7 on GitHubfix(deps): update dev-non-major (#14698)GitHub Copilot
f8798270 on GitHubchore(deps): update dependency react-devtools-core to v8 (#14689)GitHub Copilot
11e248dc on GitHubfix(portable-text): prevent duplicate nested annotation dialogs (#13551)OpenAI 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	2,055
Merge commits removed	−0
CI / dependency bots removed	−847
Considered	1,208

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 sanity-io/sanity

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	4.8%	125
2026-03	20.3%	172
2026-04	34.4%	125
2026-05	13.2%	68
2026-06	31.2%	154
2026-07	28.4%	201
2026-08	42.7%	248
2026-09	55.7%	115