Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

vllm-project/vllm ↗

vllm-project/vllm AI coding statistics: 12.5%

of 7,908 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
12.5% agent · top contributor 3.6%464 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

991
agent commits
6,917
other considered commits
464
agent contributors
3.6%
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

991assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-010%5
2026-024.7%855
2026-036.7%1078
2026-0410.8%812
2026-0513.3%888
2026-0610.9%1160
2026-0717.4%1137
2026-0814.7%1223
2026-0922.4%750

Peak month: 22.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic6758.5%
OpenAI CodexOpenAI1111.4%
Gemini CLIGoogle1091.4%
Cursor AgentAnysphere931.2%
GitHub CopilotGitHub320.4%
DevinCognition20%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0fefffc9 on GitHub[KVConnector][NIXL] Support attention-HMA layouts in pipeline-parallel pusClaude Code
  • 12575123 on GitHub[DSA] Wire DeepGEMM sparse MQA logits into the DeepSeek V4.1 indexer (#562Claude Code
  • 1e47ec00 on GitHub[Bugfix][Gemma 4] Don't read fft_length when profiling unified audio (#567Claude Code
  • 031f5810 on GitHub[Build][NVIDIA] Update public Rubin dependencies and MSA compatibility (#5OpenAI Codex
  • 0fefffc9 on GitHub[KVConnector][NIXL] Support attention-HMA layouts in pipeline-parallel pusOpenAI Codex
  • 241e9391 on GitHub[Bugfix][Attention] Stabilize sparse-MLA DCP for GLM PCP evals (#55879)OpenAI Codex
  • 6f74337c on GitHub[Bugfix][Spec Decode]Preserve user --speculative-config overrides for specGemini CLI
  • 8fea1d30 on GitHubFix uniform_random routing simulation to sample without replacement (#4368Gemini CLI
  • bf2b45b5 on GitHub[Attention] Integrate FlashAttention 4 SM100 headdim 256 support (#42669)Gemini CLI
  • 35dc2730 on GitHub[ROCm][Spec Decode] Add Aiter MLA decode support non-causal draft block (#Cursor Agent
  • 79e205e8 on GitHub[Doc] Clarify ITL vs TPOT Prometheus metrics (#55283)Cursor Agent
  • 00972dfd on GitHub[ROCm][DSV4.1][Perf] Fold the mHC post step into the delayed pre projectioCursor Agent
  • c9355e25 on GitHub[XPU][Bugfix] Add forward_xpu to Ernie4_5_VLRotaryEmbedding (#55942)GitHub Copilot
  • 6fd08c45 on GitHub[XPU][Bugfix] Fix FalconH1 pipeline-parallel execution (#55913)GitHub Copilot
  • a0d3e5c1 on GitHub[XPU] Add fused GemmaRMSNorm path for eager execution (#53678)GitHub Copilot
  • d3d79ffc on GitHub[Bugfix][Spec Decode] Capture the widest uniform decode batch by default (Devin
  • 044b0522 on GitHub[Kernel][Perf] Tune fused_moe FP8 config for Qwen3.5 on L40S (+7%) (#53819Devin

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 window7,911
Merge commits removed−0
CI / dependency bots removed−3
Considered7,908

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
vllm-project/vllm
Default branch
main
Resolved HEAD
6a2fdf9ac6f929f937dbe4617f1993c068045f81 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position67th percentile

Midrank percentile; equal shares split the tied positions.

Repository
12.5%
Cohort median
6.3%
Share rank
82 / 247
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 247.

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 →Devin commitsBrowse repositories with detected Devin signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Gemini CLI commitsBrowse repositories with detected Gemini CLI signatures →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 vllm-project/vllm

Scan another repository

Try