Japan-built · Japanese-primary · Cautious AI adoption

A cabinet model for AI work, from Japan.

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

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.

Built for careful adoption

Japanese companies often ask where AI may act, who remains accountable, and what evidence remains. Naikaku makes those boundaries visible.

From automation and research work

The system is shaped for customer automation needs, research loops, investigation workflows, and engineering checks.

Public source from Japan

EMYSTI is releasing the approach as noncommercial public source so developers can inspect, fork, and contribute.

For AI that can be used carefully.

AI adoption in Japan often has to satisfy legal, information-control, quality, and customer-explanation concerns. Naikaku responds by separating proposal from execution and putting reviewable evidence at the center.

Business automation

Run repetitive work, research, reports, and code checks with scoped permissions and evidence.

Research workflows

Compare model viewpoints, critique, retry, and preserve records in the same workspace.

Engineering teams

Even when an AI runner performs work, receipts and artifact review keep final acceptance explicit.

EMYSTI Hero Series

Naikaku is the thinking and execution layer behind the Hero Series.

VisitHero, TransHero, StayHero, and HanasuHero are not isolated app ideas. Naikaku is the EMYSTI AI workbench that helps separate planning, verification, translation, implementation, and supervision before work reaches people in the field.

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.