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.

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

01Result

waybarrios/vllm-mlx ↗

waybarrios/vllm-mlx AI coding statistics: 17.8%

of 482 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
17.8% agent · top contributor 43%19 contributors
org-wide

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

86
agent commits
396
other considered commits
19
agent contributors
43%
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

85assisted
1autonomous

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
2026-0227.9%43
2026-035.1%39
2026-0415.7%229
2026-059.1%44
2026-0623.1%39
2026-070%4
2026-0820%60
2026-0945.8%24

Peak month: 45.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic8417.4%
GitHub CopilotGitHub20.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • edfcfacd on GitHubfix(registry): detect and reap dead engines instead of reporting loaded foClaude Code
  • 2b766a9f on GitHubfix(tool-parsers): dispatch GLM-4.7 native tool calls from AutoToolParserClaude Code
  • 2680dedf on GitHubchore: remove dead code across model_runner, platform detection, engine inClaude Code
  • 99a5d5cf on GitHubci: restack Python 3.13 anyio coverage (#312)GitHub Copilot
  • 85821197 on GitHubUpdate vllm-mlx --model CLI docs to show two vllm-mlx serve variants with GitHub 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 window552
Merge commits removed−70
CI / dependency bots removed−0
Considered482

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 →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 waybarrios/vllm-mlx

Scan another repository

Try