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.

TokenHub gives enterprises a private gateway to unify AI model access and governance, making every request controllable, traceable, and attributable.

01Result

astaxie/TokenHub ↗

astaxie/TokenHub AI coding statistics: 3.8%

of 1,307 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

3.8% agent · top contributor 62%6 contributors

team

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

agent commits

1,257

other considered commits

agent contributors

62%

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

50assisted

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: 16.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	44	3.4%
Cursor Agent	Anysphere	4	0.3%
GitHub Copilot	GitHub	2	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

4cb605ac on GitHubci(frontend): run admin domain unit tests in the frontend jobClaude Code
c9b23167 on GitHubfix(api-keys): search only matches key names, not serialized fieldsClaude Code
c894882f on GitHubfix(review): preserve 413 contract, fix overflow guard and anthropic 413 tClaude Code
0592dd91 on GitHubfix(i18n): template remaining API key usage phrasesCursor Agent
462e8e2e on GitHubrefactor(frontend): format numbers with the app localeCursor Agent
2aca796e on GitHubfix(store): settle quota usage in the admission periodCursor Agent
11bed15a on GitHubPotential fix for pull request findingGitHub Copilot
c14bfe7a on GitHubPotential fix for pull request findingGitHub Copilot

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	1,589
Merge commits removed	−259
CI / dependency bots removed	−23
Considered	1,307

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 →Go AI coding statisticsCompare evidence across Go 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 astaxie/TokenHub

Scan another repository

Try

Month	Agent share	Considered commits
2026-06	0%	18
2026-07	16.8%	226
2026-08	1.3%	944
2026-09	0%	119