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.

Production-grade MCP server and AI tools for the Godot engine. A Snap to install. Totally free and fun.

01Result

hi-godot/godot-ai ↗

hi-godot/godot-ai AI coding statistics: 60.9%

of 836 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

60.9% agent · top contributor 49.9%12 contributors

org-wide

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

509

agent commits

327

other considered commits

agent contributors

49.9%

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

508assisted

1autonomous

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: 73.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	493	59%
Cursor Agent	Anysphere	14	1.7%
GitHub Copilot	GitHub	3	0.4%

03Evidence

Inspect the matches

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

Matched commit samples

fe52859c on GitHubci: post to Discord when a v4 promotion run succeedsClaude Code
031d4b09 on GitHubfix: qualification servers bind loopback without resolving its nameClaude Code
d2bd1795 on GitHubfix: a phase from a launch that already exited does not cost the occupantClaude Code
bf3516b3 on GitHubfix: let Configure all run during an INCOMPATIBLE refreshCursor Agent
69ba29f7 on GitHubfix: reject a GODOT_BIN path that is a directoryCursor Agent
a9556681 on GitHubtest: isolate Windows GODOT_BIN fallbacks from os.nameCursor Agent
8652b9d7 on GitHubAdd game_manage runtime inspection and input tools (#470)GitHub Copilot
c6623a26 on GitHubFix self-update ZIP backslash test on Windows (#472)GitHub Copilot
2da47688 on GitHubSuggest recovery shapes when camera/UI rejections look transform/HUD-shapeGitHub 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	1,058
Merge commits removed	−108
CI / dependency bots removed	−114
Considered	836

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 hi-godot/godot-ai

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	73.8%	240
2026-05	58.5%	135
2026-06	43.1%	51
2026-07	62.6%	147
2026-08	38.9%	90
2026-09	60.1%	173