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.

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and model-agnostic. Currently shipping Qwen3.8-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1×/2×/4x/8x cards.

01Result

noonghunna/club-3090 ↗

noonghunna/club-3090 AI coding statistics: 79.1%

of 1,763 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
79.1% agent · top contributor 65.7%14 contributors
team

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

1,395
agent commits
368
other considered commits
14
agent contributors
65.7%
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

1395assisted
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
2026-0477.9%68
2026-0570%557
2026-0690%339
2026-0790.8%316
2026-0879%295
2026-0967.6%188

Peak month: 90.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic138878.7%
Cursor AgentAnysphere70.4%
OpenAI CodexOpenAI30.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7de401b3 on GitHubfeat(sgl/dual-max): pin K=10 and raise context to 163840 (#1331)Claude Code
  • af169b1f on GitHubdocs(qwen3.8-27b): the fp8 header table was the int4 sibling's, not a measClaude Code
  • 539860ff on GitHubdocs(qwen3.8-27b): retract the dual-fast decode regression — it was the gaClaude Code
  • 611587df on GitHubdocs(upstream): clarify #40812 is merged-but-insufficient; point at #43923Cursor Agent
  • f5d5dca0 on GitHubfix(nvlink): strip only expandable_segments on custom-AR pathCursor Agent
  • a4b8bd1d on GitHubFix NVLink boot crash when compose pre-sets expandable_segmentsCursor Agent
  • ae4846fd on GitHubdocs + charts: v7.66 + Cliff 1 mech B closed across all 4 TQ3 composesOpenAI Codex
  • 9af1a524 on GitHubPN30 dst-shaped temp fix: close DS conv state regression class on long-texOpenAI Codex
  • a62ad78a on GitHubPN25 v3: close Cliff 1 mech B (club-3090#16) on long-text via setup-time GOpenAI 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 window2,060
Merge commits removed−268
CI / dependency bots removed−29
Considered1,763

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 →Python AI coding statisticsCompare evidence across Python 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 noonghunna/club-3090

Scan another repository

Try