Ask VitContactAsk VitGet Started
ENIT

Orbis · Res

The kernel thinks. Res defines the domain.

Vitruvyan is domain-agnostic by design. The kernel stays universal, while Res lets you specialize the framework for the domain you actually operate in: healthcare, logistics, security, governance, and beyond. You define the language, the entities, the rules, and the sources of truth. The kernel turns that domain into a cognitive system.

Kernel

Stable cognitive infrastructure, unchanged across domains.

Perception
ingestion, parsing, normalization
Memory
semantic storage with provenance
Reasoning
verification, scoring, explanation

Res field

HealthcareOperationsLegal
Entities
patient, symptom
Signals
lab result, clinical note
Rules
triage, verify, explain

Live demo · Finance Res

Mercator is a finance Res built on Vitruvyan. Ask questions about stocks, portfolios and market signals in natural language — every answer comes with a traceable reasoning chain, source attribution, and an explicit confidence score. No black boxes.

Try Mercator

What is Res

A thin domain layer, not a rebuild.

Res is a thin domain layer that sits on top of the Vitruvyan kernel. It contains three things: a vocabulary (what entities exist in your domain), connectors (where data comes from), and rules (domain-specific validation and business logic).

The kernel provides the cognitive infrastructure — ingestion pipelines, semantic memory, LLM orchestration, reasoning chains, audit trails. Res doesn't rebuild any of that. It configures it.

Think of it like a database schema: you define the shape of your domain, and the system knows how to store, query, reason about, and validate it. Except here, the system also knows how to perceive, remember, and explain its reasoning.

You don't need to understand the kernel internals. You need to understand your domain. That's where your expertise goes.

From zero to deployed

Four steps. No boilerplate.

The CLI scaffolds the structure, you fill in the domain knowledge, and deploy.

  1. /01

    Scaffold

    vit vertical create my-domain

    One command generates the full vertical structure: entity definitions, domain connectors, validation rules, and a ready-to-use manifest. You start with a working skeleton, not a blank page.

  2. /02

    Define

    my-domain/vertical_manifest.yaml

    Declare your domain vocabulary — entities, relationships, signals. The manifest tells the kernel what your domain looks like. No code required at this stage — just configuration.

  3. /03

    Connect

    my-domain/connectors/

    Write thin adapters for your data sources — APIs, databases, file systems, IoT streams. The kernel handles ingestion, normalization, and semantic indexing. You just point it at the data.

  4. /04

    Deploy

    vit vertical deploy my-domain

    Your vertical plugs into the running kernel. Perception, memory, reasoning, verification — all active. Every output carries provenance, confidence scores, and a full audit trail. From day one.

What Res gets from the kernel

Every Res inherits the full cognitive stack.

You don't build these — they're already running.

  • Perception pipeline

    Ingestion, parsing, entity extraction, language detection, normalization. Data enters clean.
  • Semantic memory

    Vector storage, coherence scoring, temporal decay, retrieval with provenance. The system remembers.
  • Reasoning engine

    LLM orchestration, chain-of-thought tracing, confidence scoring. Every conclusion is traceable.
  • Verification layer

    Invariant checks, contradiction detection, source cross-referencing. Nothing ships unchecked.
  • Audit trail

    Every input, every decision, every output — logged immutably. Full reproducibility.
  • Event bus

    Redis Streams-based cognitive transport. Services communicate asynchronously. Payload-blind by design.

Example Res

Reference implementations, one kernel.

How different domains plug into the same kernel.

Featured Res

A reference Res for operations shows how the same kernel can coordinate workflows, audits, and explainable decisions.

It shows what Res looks like in a real operating context: decision support, workflow memory, and verification built on top of the same kernel.

Build a Res
  • Operations Res

    Operations

    Workflow reasoning, exception handling, operational memory, and explainable process intelligence

    workflow-memoryprocess-monitoraudit-ledger
  • Healthcare Res

    Healthcare

    Clinical reasoning, differential diagnosis, patient memory

    patient-intakeclinical-memorydiagnosis-engine
  • Legal Res

    Legal

    Contract analysis, precedent search, compliance verification

    contract-parserprecedent-memorycompliance-engine
  • Industrial Res

    Industrial

    Predictive maintenance, anomaly detection, sensor fusion

    sensor-intakeanomaly-detectormaintenance-planner

Ready to build?

The kernel is ready. Your domain is next.

Install Vitruvyan, scaffold your Res, and start building.