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.

Codex2API 是一个基于 Go + Gin + React/Vite 的 Codex 反向代理与管理后台项目

01Result

james-6-23/codex2api ↗

james-6-23/codex2api AI coding statistics: 8.3%

of 1,642 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

8.3% agent · top contributor 47.1%6 contributors

team

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

136

agent commits

1,506

other considered commits

agent contributors

47.1%

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

136assisted

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	75	4.6%
Cursor Agent	Anysphere	60	3.7%
GitHub Copilot	GitHub	1	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

15bfd437 on GitHubrefactor(settings): retire strict first-token mode, always record loose fiClaude Code
f52a4421 on GitHubfix(antigravity): support input_image in function_call_outputClaude Code
6a8154e1 on GitHubfix(antigravity): support input_image in Responses adapterClaude Code
b66c1bf0 on GitHubfix(retry): classify status-less upstream Do failures as transportCursor Agent
f43ed98b on GitHubfix(prompt-policy): reject Moderations request mode for CY attributionCursor Agent
4e1fecfd on GitHubfix(billing): normalize independent alias pricing lookupsCursor Agent
4aa1b7c0 on GitHubchore: Add explanationGitHub 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	1,909
Merge commits removed	−267
CI / dependency bots removed	−0
Considered	1,642

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 james-6-23/codex2api

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	14.7%	218
2026-04	1.5%	130
2026-05	16.8%	191
2026-06	4.1%	146
2026-07	0%	305
2026-08	13.9%	438
2026-09	1.4%	214