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.

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

01Result

vllm-project/guidellm ↗

vllm-project/guidellm AI coding statistics: 4.9%

of 526 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

4.9% agent · top contributor 42.3%12 contributors

org-wide

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

agent commits

500

other considered commits

agent contributors

42.3%

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

26assisted

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

Peak month: 15.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	19	3.6%
Cursor Agent	Anysphere	7	1.3%
GitHub Copilot	GitHub	1	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

6eab76f6 on GitHubFix invalid format placeholder in mock server error logging (#1142)Claude Code
8f834daf on GitHubAdd multimodal support to the mock server (#1056)Claude Code
00a530bd on GitHubPull pending requests into a worker only when a consumer is waiting (#1042Claude Code
a45301db on GitHubAdd vLLM Python batch backend for micro-batched inference (#736)Cursor Agent
63790056 on GitHubSubagent Conversation Support (#935)Cursor Agent
35537470 on GitHubFix worker status for unusable terminal backend responses (#615)Cursor Agent
f923ba5f on GitHubApply suggestions from code reviewGitHub 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 window	664
Merge commits removed	−93
CI / dependency bots removed	−45
Considered	526

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 →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/guidellm

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	2.5%	40
2026-03	0%	178
2026-04	9.7%	31
2026-05	7.6%	118
2026-06	3.4%	59
2026-07	10.8%	37
2026-08	15.2%	33
2026-09	6.7%	30