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.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

01Result

lidge-jun/opencodex ↗

lidge-jun/opencodex AI coding statistics: 4.7%

of 8,956 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4.7% agent · top contributor 74.6%25 contributors
team

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

418
agent commits
8,538
other considered commits
25
agent contributors
74.6%
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

418assisted
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
2026-0629.8%704
2026-072.8%2117
2026-081.9%4118
2026-093.4%2017

Peak month: 29.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic3654.1%
Cursor AgentAnysphere470.5%
OpenAI CodexOpenAI40%
GitHub CopilotGitHub20%

03Evidence

Inspect the matches

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

Matched commit samples

  • 17b3d3fe on GitHubfix(claude): preserve Go affinity through final combo dispatchClaude Code
  • af7c114a on GitHubdocs(devlog,structure): record the PR6 review round and name hub-state ownClaude Code
  • fe65afe7 on GitHubtest(server): pin that /v1/hub-state stays off the unauthenticated loopbacClaude Code
  • ab3bc195 on GitHubdocs(codex-home): say which refusals still compensate after #4531 (#4552)Cursor Agent
  • a84e6e82 on GitHubfix(codex): scope the history preflight to the relabel unit (#4531)Cursor Agent
  • 954c1f28 on GitHubfix(claude): make harness cache-prefix stabilization explicitly opt-inCursor Agent
  • d11f1e65 on GitHubfeat(responses): opt in to client transport hint suppressionOpenAI Codex
  • 3ee6f371 on GitHubdocs(devlog): open the account pool unification unit (#4275)OpenAI Codex
  • a1304174 on GitHubfix(responses): land the workstream-A Responses compatibility stack (#3942OpenAI Codex
  • 9296f2d5 on GitHubClarify apply patch envelopeGitHub Copilot
  • 1b06c712 on GitHubfix(chat-completions): address Copilot App review blockersGitHub 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 window11,053
Merge commits removed−2,077
CI / dependency bots removed−20
Considered8,956

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 lidge-jun/opencodex

Scan another repository

Try