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.

Gen1Recomp - A native Lua / LÖVE2D recreation of Gen 1, 2, and 3 Poke

01Result

bryanthaboi/gen1recomp ↗

bryanthaboi/gen1recomp AI coding statistics: 16.6%

of 971 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

16.6% agent · top contributor 77%10 contributors

team

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

161

agent commits

810

other considered commits

agent contributors

77%

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

161assisted

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: 20.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	128	13.2%
Claude Code	Anthropic	23	2.4%
GitHub Copilot	GitHub	10	1%

03Evidence

Inspect the matches

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

Matched commit samples

ef208035 on GitHubFix Gen1Tls.lua encoding (was UTF-16).Cursor Agent
18d61779 on GitHubHang gen1tls on love.system and forward tls* through LegacyCompat.Cursor Agent
7e57e317 on GitHubShip gen1tls.dll in Windows release zips.Cursor Agent
dd2a1f89 on GitHubengine: opts.items -- items on the link cable, for a mode that asks (RFC 0Claude Code
0cb5babd on GitHubci: stop asking setup-android for the retired `tools` packageClaude Code
5920402d on GitHubGen 2: a cart saves into its own scope, not the base game'sClaude Code
f6068402 on GitHubHandle non-JSON update responsesGitHub Copilot
ae1b59ce on GitHubfix: restore wild encounter grace periodGitHub Copilot
02c4de89 on GitHubFix champion rival walk-out routeGitHub 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	1,607
Merge commits removed	−529
CI / dependency bots removed	−107
Considered	971

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 →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 bryanthaboi/gen1recomp

Scan another repository

Try

Month	Agent share	Considered commits
2026-07	3.8%	157
2026-08	20.8%	731
2026-09	3.6%	83