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.

Cost-efficient and pluggable Infrastructure components for GenAI inference

01Result

vllm-project/aibrix ↗

vllm-project/aibrix AI coding statistics: 3.1%

of 512 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.1% agent · top contributor 6.3%16 contributors
org-wide

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

16
agent commits
496
other considered commits
16
agent contributors
6.3%
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

16assisted
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
2026-020%30
2026-037.9%38
2026-040%62
2026-051.5%66
2026-061%105
2026-074.1%73
2026-085.3%75
2026-096.3%63

Peak month: 7.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic81.6%
Gemini CLIGoogle40.8%
GitHub CopilotGitHub40.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7a7e7bb9 on GitHubfix(modeladapter): drop max loading retries cap (#2710)Claude Code
  • 9359e676 on GitHub[Bug] Allows for resumable downloads after a failure when loading model adClaude Code
  • 991fb82c on GitHub[Misc] Add KVCache controller integration tests (#2648)Claude Code
  • 140e5238 on GitHub[UI] Add UI for aiconfigurator tool (#2649)Gemini CLI
  • 23cf68cf on GitHub[Docs] Fix incorrect script names, flags, and module path in gpu_optimizerGemini CLI
  • 4dcc6bf6 on GitHubfeat(modelclaim): add Grafana dashboard for high-density runtime pools (#2Gemini CLI
  • 9542c904 on GitHub[Feat] Add Dynamo provider support to brixbench (#2469)GitHub Copilot
  • 824980a6 on GitHubfix: resolve trtllm metrics showing undefined model_name and engine_type (GitHub Copilot
  • 24490103 on GitHub[App][API] Centralize default model names in config for easy switching (#2GitHub 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 window512
Merge commits removed−0
CI / dependency bots removed−0
Considered512

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI signatures →Go AI coding statisticsCompare evidence across Go 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/aibrix

Scan another repository

Try