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.

Pocket Casts iOS app 🎧

01Result

Automattic/pocket-casts-ios ↗

Automattic/pocket-casts-ios AI coding statistics: 25.1%

of 3,749 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

25.1% agent · top contributor 37.3%23 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

940

agent commits

2,809

other considered commits

agent contributors

37.3%

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

936assisted

4autonomous

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: 51.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	854	22.8%
GitHub Copilot	GitHub	78	2.1%
Cursor Agent	Anysphere	6	0.2%
OpenAI Codex	OpenAI	2	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

8b29c6a6 on GitHubStop hiding What's New messages published before the account was createdClaude Code
431d4901 on GitHubMake a What's New page image optional, along with its size and alt textClaude Code
b88ff57d on GitHubList only the What's New locales published under a regionClaude Code
93c25e01 on GitHubPotential fix for pull request findingGitHub Copilot
3515f8b8 on GitHubImprove accessibilityGitHub Copilot
d9542322 on GitHubOnly update title if one existsGitHub Copilot
1a73c767 on GitHubShow playlist limit toast earlier in the add-to-playlist flowCursor Agent
8f8eaa34 on GitHubFix playlist limit toast being immediately replaced by "Added to 0 playlisCursor Agent
da2308de on GitHubShow remove option when episode is already in Up NextCursor Agent
5d4d0988 on GitHubClose credential template file safelyOpenAI Codex
8213d40f on GitHubAdd create-pr skill frontmatterOpenAI Codex

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	5,262
Merge commits removed	−1,308
CI / dependency bots removed	−205
Considered	3,749

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Swift AI coding statisticsCompare evidence across Swift 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 Automattic/pocket-casts-ios

Scan another repository

Try

Month	Agent share	Considered commits
2026-01	0%	2
2026-02	5.7%	442
2026-03	11.3%	344
2026-04	21.7%	446
2026-05	18.1%	757
2026-06	32.1%	604
2026-07	45.8%	612
2026-08	25%	420
2026-09	51.6%	122