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.

NyameBox, The Original NekoBox Rebranded, the cross-platform Qt proxy utility, empowered by sing-box and thrift

01Result

qr243vbi/nekobox ↗

qr243vbi/nekobox AI coding statistics: 0.9%

of 2,032 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

0.9% agent · top contributor 63.2%3 contributors

individual

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

agent commits

2,013

other considered commits

agent contributors

63.2%

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

19assisted

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: 71.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	12	0.6%
Cursor Agent	Anysphere	7	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

2c56948e on GitHubfeat: update a profile in place from a link or fileClaude Code
4bdfbc3c on GitHubfeat: import AmneziaWG profiles from Amnezia's vpn:// linksClaude Code
d6ef16d7 on GitHubfix: export AWG s3/s4 with their own values, keep the AWG local addressClaude Code
1004c515 on GitHubHide TUN DNS noise and coalesce log floods to stop Windows UI freezesCursor Agent
5b751174 on GitHubFix Windows freeze, .exe routes, and nekobox-core connection noiseCursor Agent
793f2fd1 on GitHubDo not trust an incomplete golang cache in CICursor 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	2,061
Merge commits removed	−29
CI / dependency bots removed	−0
Considered	2,032

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 →C++ AI coding statisticsCompare evidence across C++ 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 qr243vbi/nekobox

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	49
2026-03	0%	495
2026-04	0%	439
2026-05	0%	191
2026-06	0%	653
2026-07	6.4%	188
2026-08	20%	10
2026-09	71.4%	7