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.

External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.

01Result

duolahypercho/codex-router ↗

duolahypercho/codex-router AI coding statistics: 28.5%

of 1,148 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
28.5% agent · top contributor 72.2%14 contributors
team

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

327
agent commits
821
other considered commits
14
agent contributors
72.2%
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

327assisted
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
2026-078.5%129
2026-0823.4%766
2026-0954.2%253

Peak month: 54.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic25222%
Cursor AgentAnysphere756.5%
OpenAI CodexOpenAI10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 957cc6dc on GitHubchore: release v0.6.0Claude Code
  • c8af2a93 on GitHubcuration: keep only publishable input modalities (text, image) from an advClaude Code
  • 9cdeb1df on GitHubcuration: describe catalog-advertised sizing and modalities as such, not aClaude Code
  • b1680923 on GitHubtest: expect empty advertised inputModalities on Chutes fixture discoveryCursor Agent
  • f4dce80d on GitHubfix: expose picker-order on Windows and bound Ollama show transport failurCursor Agent
  • 9f8fe1c3 on GitHubfix: keep Usage up when a balance currency is not ISO 4217Cursor Agent
  • b944249d on GitHubfix: enforce routed subagent provider affinity (#632)OpenAI Codex

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 window1,603
Merge commits removed−438
CI / dependency bots removed−17
Considered1,148

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →JavaScript AI coding statisticsCompare evidence across JavaScript 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 duolahypercho/codex-router

Scan another repository

Try