Pulse
2026-09-18-v3.0
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.

OpenAI-compatible proxy for ChatGPT Codex Responses API

01Result

icebear0828/codex-proxy ↗

icebear0828/codex-proxy AI coding statistics: 21.4%

of 757 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
21.4% agent · top contributor 87%8 contributors
individual

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

162
agent commits
595
other considered commits
8
agent contributors
87%
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

162assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0297.3%73
2026-0336.4%225
2026-040%79
2026-051.3%156
2026-060%61
2026-0711.1%9
2026-083.7%81
2026-094.1%73

Peak month: 97.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic16121.3%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 131c7685 on GitHubdocs(docker): document memory limits, default mem_limit + NODE_OPTIONSClaude Code
  • 0d12559e on GitHubfix(proxy): 确定性的工具 schema 校验错误按 400 上报，不再当可重试 5xxClaude Code
  • ecdbfaed on GitHubfix(translation): 清洗上游正则引擎编译不了的 tool schema patternClaude Code
  • 7af1bf34 on GitHubfix(translation): preserve OpenAI function tool strict (#441)Cursor 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 window1,129
Merge commits removed−157
CI / dependency bots removed−215
Considered757

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 icebear0828/codex-proxy

Scan another repository

Try