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.

Official Anytype client for MacOS, Linux, and Windows

01Result

anyproto/anytype-ts ↗

anyproto/anytype-ts AI coding statistics: 49.6%

of 2,583 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

49.6% agent · top contributor 79.5%9 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

1,280

agent commits

1,303

other considered commits

agent contributors

79.5%

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

1280assisted

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: 68.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1279	49.5%
Cursor Agent	Anysphere	2	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

2b349f4d on GitHubfeat(import): import v2 client integration and target channel pickerClaude Code
12a23e05 on GitHubJS-9867: fix tooltip clipping near the window bottom edgeClaude Code
3e574d94 on GitHubJS-9867: info button + hint for the prefer-TCP toggleClaude Code
6dd9d7ae on GitHubFix object open after space switchCursor Agent
8e581c95 on GitHubJS-2195: align Excalidraw fullscreen top menu flush left on macOSCursor Agent

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	3,011
Merge commits removed	−428
CI / dependency bots removed	−0
Considered	2,583

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 →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 anyproto/anytype-ts

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	47.2%	633
2026-03	68.9%	729
2026-04	59.1%	675
2026-05	53.9%	128
2026-06	4.3%	94
2026-07	2.9%	105
2026-08	1.6%	182
2026-09	2.7%	37