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.

On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects.

01Result

tmoroney/auto-subs ↗

tmoroney/auto-subs AI coding statistics: 20%

of 455 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

20% agent · top contributor 63.7%7 contributors

team

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

agent commits

364

other considered commits

agent contributors

63.7%

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

33assisted

58autonomous

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: 50%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Devin	Cognition	65	14.3%
Claude Code	Anthropic	22	4.8%
Cursor Agent	Anysphere	3	0.7%
GitHub Copilot	GitHub	1	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

6f631bab on GitHubaddress greptile review feedback (greploop iteration 2)Devin
7506c531 on GitHubFix preview rendering: read frame via Output:GetValue/Image:SaveAs, drop cDevin
496ac306 on GitHubaddress greptile review feedback (greploop iteration 1)Devin
bcdbd308 on GitHubfix: don't map SOCKS-only proxy entries to HTTP_PROXYClaude Code
d1af90a6 on GitHubfix: update Cargo.lock and add NO_PROXY for loopback addressesClaude Code
cea6c140 on GitHubFix migrateCustomPrompt to only strip legacy headers when detectedClaude Code
e69f365f on GitHubfeat(resolve): expose text wrap on the animated caption macroCursor Agent
d550a2d2 on GitHubfix(resolve): integerize GeneratePreview clip lengthCursor Agent
e0bca985 on GitHubfix(resolve): integerize caption frames for AppendToTimelineCursor Agent
d0f0f04a 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	536
Merge commits removed	−81
CI / dependency bots removed	−0
Considered	455

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 →Devin commitsBrowse repositories with detected Devin signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 tmoroney/auto-subs

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	4.8%	21
2026-03	4.2%	24
2026-04	7.4%	108
2026-05	3.6%	84
2026-06	14.9%	67
2026-07	45.3%	128
2026-08	50%	6
2026-09	41.2%	17