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.

Make any agent harness multimodal-native.

01Result

QwenLM/Qwen-MM-Plugins ↗

QwenLM/Qwen-MM-Plugins AI coding statistics: 9.1%

of 154 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

9.1% agent · top contributor 57.1%4 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

agent commits

140

other considered commits

agent contributors

57.1%

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

14assisted

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: 12.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	9	5.8%
Cursor Agent	Anysphere	5	3.2%

03Evidence

Inspect the matches

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

Matched commit samples

2ee3ef8f on GitHubdocs(cookbooks): add real blender and freecad casesClaude Code
8f43c979 on GitHubdocs: unify capability descriptions + note swappable providersClaude Code
e38f69a2 on GitHubdocs: generalize core description + fix stale auto-discovery noteClaude Code
ed79b65a on GitHubfix(core): declare viz/pypdfium2 for LaTeX SYSTEM_DEPSCursor Agent
544fc285 on GitHubtest: read plugin manifests as UTF-8Cursor Agent
7045c824 on GitHubdocs(core): drop stale cloud-tool claims from plugin manifestsCursor Agent

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	203
Merge commits removed	−49
CI / dependency bots removed	−0
Considered	154

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 →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 QwenLM/Qwen-MM-Plugins

Scan another repository

Try

Month	Agent share	Considered commits
2026-08	12.7%	110
2026-09	0%	44