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.

A framework for efficient model inference with omni-modality models

01Result

vllm-project/vllm-omni ↗

vllm-project/vllm-omni AI coding statistics: 8.8%

of 2,494 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
8.8% agent · top contributor 11.4%88 contributors
org-wide

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

220
agent commits
2,274
other considered commits
88
agent contributors
11.4%
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

220assisted
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
2026-025%181
2026-031.4%354
2026-047.4%364
2026-059.3%343
2026-0613.1%305
2026-0710.8%286
2026-089%411
2026-0915.6%250

Peak month: 15.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1536.1%
Cursor AgentAnysphere471.9%
GitHub CopilotGitHub271.1%
OpenAI CodexOpenAI40.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 85da9433 on GitHub[Refactor][Diffusion] Complete generic backend plan consumption (#7313)Claude Code
  • 1b7e854b on GitHub[Bugfix][MiniCPM-o] Attach a unit's whole frame group and size the vision Claude Code
  • e8f45fcd on GitHub[Frontend] Add ComfyUI FastH3 node, fix t2va aspect ratio and dropped audiClaude Code
  • c17126c2 on GitHub[Model] Add Gepard-1.0 OpenAI /v1/audio/speech serving (#7499)Cursor Agent
  • 64903b8e on GitHub[CI/Build] Share nightly CUDA YAML between H100/L4 and B200 (#7028)Cursor Agent
  • e284d907 on GitHub[Perf][Frontend] Chunk in-memory image file responses (#7459)Cursor Agent
  • 5e4b9f8c on GitHub[Misc] Align CODEOWNERS with module/feature design docs (#5958)GitHub Copilot
  • b6728db4 on GitHub[Frontend] Add ComfyUI support for r2v (MiniMax H3 as example) (#5756)GitHub Copilot
  • 0a51a185 on GitHub[Bugfix] Leave MiniCPM-o vocoder memory headroom (#5621)GitHub Copilot
  • 78934753 on GitHub[Tests] Test image edit input limits in tiny model framework (#7434)OpenAI Codex
  • ed377664 on GitHub[Tests] Skip global GPU cleanup for parallel online diffusion tests (#7534OpenAI Codex
  • d3493384 on GitHub[BugFix] Fix leftovers of the legacy OpenAI realtime API event names (#742OpenAI 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 window2,494
Merge commits removed−0
CI / dependency bots removed−0
Considered2,494

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 →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 vllm-project/vllm-omni

Scan another repository

Try