Pulse
2026-09-18-v3.0
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.

Python script to update metadata information for items in plex as well as automatically build collections and playlists. The Wiki Documentation is linked below.

01Result

Kometa-Team/Kometa ↗

Kometa-Team/Kometa AI coding statistics: 1.3%

of 396 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.3% agent · top contributor 80%2 contributors
individual

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

5
agent commits
391
other considered commits
2
agent contributors
80%
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

5assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020%20
2026-030%10
2026-040%19
2026-054.2%24
2026-060%101
2026-070%104
2026-086.2%65
2026-090%53

Peak month: 6.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic30.8%
GitHub CopilotGitHub20.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • 137f7328 on GitHubFix CLI args resetting to defaults under Python 3.14's forkserver default Claude Code
  • 1fc6051b on GitHubFix resolution overlay's edition_dovetail wrongly winning over plain editiClaude Code
  • fac58efe on GitHubfix: accept "popcorn" as alias for "tomatoesaudience" in MDBList ratings (Claude Code
  • 905f6fc8 on GitHubReduce MDBList API usage with bulk prefetching (#3509)GitHub Copilot
  • 94d7c16b on GitHubAdd direct Plex ID builders (#3497)GitHub 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 window415
Merge commits removed−0
CI / dependency bots removed−19
Considered396

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 Kometa-Team/Kometa

Scan another repository

Try