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.

Real-time two-way speech translation for bilingual meetings — auto-detects the spoken language and translates both directions, cloud or fully offline on-device. Desktop (Windows · macOS · Linux) + browser extension (Chrome · Edge) for Zoom, Meet, Teams & any app.

01Result

kizuna-ai-lab/sokuji ↗

kizuna-ai-lab/sokuji AI coding statistics: 70.8%

of 2,589 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

70.8% agent · top contributor 95%5 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

1,833

agent commits

756

other considered commits

agent contributors

95%

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

1828assisted

5autonomous

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: 96.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1825	70.5%
GitHub Copilot	GitHub	8	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

fb384d84 on GitHubchore(release): v0.41.0Claude Code
be8c4519 on GitHubfix(openai-live): drop the noise floor Live streams between utterancesClaude Code
b327be16 on GitHubfix(logs): collapse the Live API's mic appends like the other OpenAI variaClaude Code
123a7d2c on GitHubfix(tts): address Supertonic 3 review feedback — quote normalization, storGitHub Copilot
65afe830 on GitHubPotential fix for pull request findingGitHub Copilot
2a9b46d7 on GitHubUpdate src/components/MainPanel/MainPanel.tsxGitHub 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	2,789
Merge commits removed	−200
CI / dependency bots removed	−0
Considered	2,589

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 →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 kizuna-ai-lab/sokuji

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	96.8%	62
2026-03	93.7%	268
2026-04	78.6%	103
2026-05	78.4%	403
2026-06	64.1%	410
2026-07	63.3%	616
2026-08	55.8%	441
2026-09	79%	286