Japanese-primary · Multi-model AI · Governed runners

AI work should pass through a cabinet.

Naikaku brings planning, coding runners, sandbox execution, critique, supervision, and evidence-based iteration into one governed workbench.

Naikaku AI workbench screen

One mission, multiple roles, reviewable evidence.

Instead of handing work to one unchecked model, Naikaku separates planning, execution, critique, supervision, safety, memory, and scoring. Execution sits behind presets, readiness checks, logs, receipt review, and artifact audit.

Cabinet governance

Separate AI roles propose, execute, critique, supervise, and leave decisions for each loop.

Bring your own API

Designed for OpenAI-compatible endpoints, OpenRouter, Anthropic, Aliyun DashScope/Qwen, Gemini, and local models.

Mac and local runners

Codex CLI, Claude Code, OpenHands, OpenClaw-style tools, Hammerspoon, and similar CLIs can be attached as governed runners.

The shortest path to try the public preview.

Start locally, check provider aliases and the gateway, then attach runner presets only when you need them. Raw API keys should stay out of browser storage.

Choose by intent.

Try it, connect APIs, supervise a Mac runner, or contribute. Each entry point keeps the same language structure.

Same content structure across languages.

Japanese stays the primary language, while English and Chinese keep matching pages, matching routes, and matching license boundaries.

日本語

The same content structure is available.

English

The same content structure is available.

简体中文

The same content structure is available.

FAQ

What does Naikaku do?

It is an AI cabinet workbench where multiple roles plan, execute, critique, supervise, score, and preserve evidence.

Can I use my own API keys?

Yes. Each role can use its own provider, endpoint, model, and API-key alias.

Can I use it commercially?

The public release is for noncommercial use. SaaS, client delivery, commercial modification, and paid integration require written permission from EMYSTI LLC.