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.

MPV-Based Jellyfin Client with Offline Sync

01Result

jellyfin/jellyfin-mpv-shim ↗

jellyfin/jellyfin-mpv-shim AI coding statistics: 92.2%

of 1,187 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

92.2% agent · top contributor 99.8%3 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

1,095

agent commits

other considered commits

agent contributors

99.8%

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

1095assisted

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: 98.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1094	92.2%
GitHub Copilot	GitHub	1	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

c804c02c on GitHubTrickplay frames are drawn at the display's scale, not the server'sClaude Code
a1ba3633 on GitHubA multimedia keyboard's Back and Forward keys page the libraryClaude Code
bf8308cc on GitHubGive the aspect force one order and one owner of the defaultClaude Code
ab630624 on GitHubImplement path expansion based on sdaqo's feedbackGitHub 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	1,747
Merge commits removed	−131
CI / dependency bots removed	−429
Considered	1,187

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 jellyfin/jellyfin-mpv-shim

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	2
2026-03	0%	8
2026-04	11.1%	9
2026-05	42.1%	19
2026-06	89.8%	49
2026-07	95.1%	508
2026-08	92.2%	385
2026-09	98.6%	207