Sushi Kitchen
組み立て · assemble

Adapt Trusts & Estates — Estate Plan.

You started from a complete Recipe, so the technology is already here for a human reason. Inspect those reasons, remove or replace anything you do not want, then save the result as the canonical Recipe or as your own explicit Variant.

Delivery model

84 of 93 rolls are open both ways, so the choice stays open until you make it. Nothing is hidden from the shelf — the board warns instead.

Requirements
All met
most rolls require nothing, which is normal
Availability
Not chosen
both models stay open until you choose
Footprint
12 cores · 18.8 GB RAM
GPU required
Review RecipeReview the open Recipe facts below. Open the Kitchen portal when you want to save the Recipe or work with Tsugiita.
Current Recipe
11 rolls
Ollamahosomaki

Provides local model execution where the owning legal deployment separately authorizes model use.

Local runtime that downloads, quantises and runs open-weight language models, exposing them over its own HTTP API and an OpenAI-compatible endpoint. Also serves embedding models.

2 cores · 4 GB
Open WebUInigiri

Provides a private chat-style interface for local model access; it is not a legal-advice surface by itself.

Self-hosted chat interface for local and remote language models, adding document retrieval, model switching, per-user workspaces, tool calling and an extensible pipeline layer.

1 core · 1 GB
Caddydragon

Provides TLS termination and reverse-proxy routing for the reusable Kitchen architecture.

Web server and reverse proxy that obtains and renews TLS certificates automatically, supports HTTP/3, and is configured either by a short text file or entirely over an API.

0.5 core · 0.25 GB
PostgreSQLfutomaki

Provides durable relational persistence for applications built on the starting architecture.

Relational database with strong SQL conformance, MVCC transactions and an extension system. This image ships the pgvector extension, adding vector columns and approximate nearest-neighbour search.

1 core · 2 GB
cAdvisorinari

Provides container resource observation so the deployment can be operated rather than treated as a black box.

Container resource monitor that discovers running containers automatically and exports per-container CPU, memory, filesystem and network statistics in Prometheus format and a built-in live view.

0.5 core · 0.5 GB
AnythingLLMhosomaki

Provides a document-oriented RAG workspace in the canonical Kitchen knowledge layer.

Retrieval-augmented chat workspace bundling document ingestion, embedding, vector storage and multi-provider model connectivity into one container. Answers cite the source passages they were drawn from.

1 core · 2 GB
Qdrantfutomaki

Provides semantic vector search for approved document-derived data.

Vector database written in Rust, pairing dense and sparse vectors with structured payloads so that metadata filters and nearest-neighbour search are resolved together in a single query.

2 cores · 4 GB
LiteLLMhosomaki

Provides a model gateway while preserving explicit provider choice.

Gateway fronting more than 100 model providers behind a single OpenAI-compatible API, adding routing rules, fallback chains, retries, per-key spend limits and request logging.

1 core · 1 GB
Prometheusinari

Collects service metrics for the reusable professional deployment.

Time-series database and monitoring server that scrapes metrics endpoints on a schedule, stores samples locally, and evaluates PromQL queries, recording rules and alert conditions against them.

1 core · 2 GB
Grafanainari

Turns operational metrics into inspectable dashboards.

Dashboard and visualisation server that queries time-series, log and SQL data sources directly and renders panels, with alert rules, notification routing and dashboards defined as JSON.

1 core · 1 GB
MinIOfutomaki

Provides S3-compatible object storage in the existing canonical Legal Practice Jubako.

Object storage server with an S3-compatible API for on-premises and edge deployments, providing erasure coding, object versioning, write-once retention locks and bucket replication.

1 core · 1 GB
Pairs well · optional, never blocks
LiteLLM suggests a key-value cache — In-memory storage for caching and queues.
Open Recipe Review

Inspect Trusts & Estates — Estate Plan. Save when you are ready.

This starts from jubako.legal-practice, so every Roll arrives with a human-readable reason. You can inspect or change it here without an account; the Recipe identity and your exact Roll choices are carried into the portal.

Every declared Roll requirement is currently satisfied.

This draft is structurally ready for deeper Sushii Intelligence guidance.

Current footprint: 18.8 GB RAM · 12 CPU cores · 479 GB storage · GPU required.
Ready to ship

Nothing left to resolve.

11 rolls · every requirement met · both delivery models open · 18.8 GB RAM · GPU required

Review Recipe

The open Builder does not charge for composition facts or the right to use the stack. Durable account work lives in the Kitchen portal; Tsugiita is the optional paid guidance layer.

This composition provides
Chat interfaceContainer metricsDashboardsDatabaseEmbeddingsLanguage model APIModel gatewayMetricsMonitoringObject storageRetrieval chatReverse proxyVector database
A running kitchen usually wants
DatabaseIn this build
Chat interfaceIn this build
MonitoringIn this build
Reverse proxyIn this build
BackupsNot yet