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.

The classic Sillytavern, now has been rewritten in Tauri/Rust.

01Result

Darkatse/TauriTavern ↗

Darkatse/TauriTavern AI coding statistics: 2.8%

of 1,281 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

2.8% agent · top contributor 66.7%6 contributors

team

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

agent commits

1,245

other considered commits

agent contributors

66.7%

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

34assisted

2autonomous

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: 13.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	24	1.9%
Claude Code	Anthropic	9	0.7%
GitHub Copilot	GitHub	3	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

07599cf5 on GitHubfix(chat): keep xhigh for OpenRouter Claude reasoning effortCursor Agent
b45acaf1 on GitHubfix(chat): normalize OpenRouter reasoning effortCursor Agent
9cbac9ef on GitHubfix(chat): accept object/array custom_* override fieldsCursor Agent
17daac6f on GitHubfix(openai): restore selected model after rebuilding custom optionsClaude Code
a2259690 on GitHubfix(openai): guard Vertex AI model select against startup raceClaude Code
f5aa50e7 on GitHubfix(ui): back the IME-commit timestamp check with an arrival-time guardClaude Code
6330e21c on GitHubPotential fix for pull request findingGitHub Copilot
1c54af61 on GitHubfix(workflows): improve package.json parse error handlingGitHub Copilot
775267f9 on GitHubfix(workflows): resolve prerelease version from package.jsonGitHub 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	1,373
Merge commits removed	−87
CI / dependency bots removed	−5
Considered	1,281

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 →JavaScript AI coding statisticsCompare evidence across JavaScript 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 Darkatse/TauriTavern

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	106
2026-03	0%	178
2026-04	1.4%	143
2026-05	13.9%	158
2026-06	6.2%	129
2026-07	0%	177
2026-08	0.8%	263
2026-09	1.6%	127