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.

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

01Result

llmsresearch/paperbanana ↗

llmsresearch/paperbanana AI coding statistics: 4.5%

of 198 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

4.5% agent · top contributor 22.2%7 contributors

team

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

agent commits

189

other considered commits

agent contributors

22.2%

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

9assisted

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: 9.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	6	3%
Cursor Agent	Anysphere	2	1%
GitHub Copilot	GitHub	1	0.5%

03Evidence

Inspect the matches

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

Matched commit samples

d458a41e on GitHubfeat: integrate Atlas Cloud provider (#220)Claude Code
fdcfd14c on GitHubfix: make critic response parsing None-safe (#219)Claude Code
e3d975a3 on GitHubfix: raise non-retryable error on empty Gemini response (#218)Claude Code
22e25941 on GitHubExpand test coverage for visualizer extraction and metadata contract.Cursor Agent
415fef1d on GitHubHandle truncated plot code fences without crashing.Cursor Agent
0cba5837 on GitHubUpdate paperbanana/cli.pyGitHub 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	323
Merge commits removed	−121
CI / dependency bots removed	−4
Considered	198

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 llmsresearch/paperbanana

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	6.2%	81
2026-03	0%	36
2026-04	2.9%	35
2026-05	0%	13
2026-06	9.4%	32
2026-09	0%	1