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.

Extracts downloads for Radarr, Sonarr, Lidarr, Readarr, and/or a Watch folder - Deletes extracted files after import

01Result

Unpackerr/unpackerr ↗

Unpackerr/unpackerr AI coding statistics: 76.6%

of 342 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

76.6% agent · top contributor 96.2%3 contributors

individual

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

262

agent commits

other considered commits

agent contributors

96.2%

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

262assisted

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: 97.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	254	74.3%
Claude Code	Anthropic	5	1.5%
GitHub Copilot	GitHub	3	0.9%

03Evidence

Inspect the matches

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

Matched commit samples

9ab47f58 on GitHubAdd system, log files, and API docs so the UI can inspect the running procCursor Agent
292494b2 on GitHubAdd settings forms so the UI can edit and test on-disk config.Cursor Agent
44bbb475 on GitHubAdd the live dashboard and history so the UI shows the unpack queue.Cursor Agent
7cef361b on GitHubfix: return nil from filterManualImportToSplitTracks when NewFiles is emptClaude Code
8a6f9e8b on GitHubfix: clean up stale/failed items from extract map to prevent memory leakClaude Code
161eda88 on GitHubfix: remove extra blank line, wrap long function signature for lll lintClaude Code
d5536dac on GitHubPotential fix for pull request findingGitHub Copilot
d7a6bae7 on GitHubPotential fix for pull request findingGitHub Copilot
000d42e9 on GitHubPotential fix for pull request findingGitHub 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	514
Merge commits removed	−148
CI / dependency bots removed	−24
Considered	342

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 →Go AI coding statisticsCompare evidence across Go 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 Unpackerr/unpackerr

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	32
2026-03	13.2%	38
2026-04	0%	1
2026-06	0%	5
2026-08	95.2%	104
2026-09	97.5%	162