menu
Neural Voyager
Context-Aware AI Orchestration
for Cyber + Spatial Ops
for Cyber + Spatial Ops
A graph‑aware exploration engine for AI agents. Neural Voyager connects models to your data layers (databases, files, APIs) via MCP‑compatible tools, builds a living map of knowledge, and plans safe read/write journeys with SoI‑aware guardrails.
MCP ProtocolsDatabase‑nativeZero‑TrustObservability
What is Neural Voyager?
Neural Voyager (NV) is XRDNA’s adaptive AI routing engine—connecting data, location, mission context, and user intent into a dynamic decision-making and automation layer.
It interprets natural input and routes it to the right models, systems, or workflows—with no-code flexibility and multi-model intelligence. It’s not just a model—it’s an AI mission brain.
Overview
What Neural Voyager Does
Connect
Bridge LLM agents to SQL/NoSQL, files, and internal APIs using MCP tools and adapters.
Explore
Traverse schemas and documents to build a knowledge graph of entities, relations, and constraints.
Safeguard
Plan queries and mutations with SoI‑aware policies, approvals, and least‑privilege scopes.
Neural Voyager brings a robust, intelligent framework for data retrieval, indexing, and processing
Whether you're handling mission-critical data, performing complex data analysis, or deploying LLMs across applications, Neural Voyager provides the infrastructure for scalable, secure, and intelligent data handling
Efficient and Scalable Data Retrieval
Access data with high precision and speed
Enhanced Insights from Complex Relationships
Uncover hidden patterns within interconnected data
Seamless LLM Integration and Management
Streamline LLM interactions with balanced load distribution and effective parsing
Adaptable and Context-Aware
Leverage embedded models for in-context data processing tailored to unique user requirements
Architecture
High‑level architecture
Pluggable tools, typed plans, and policy‑gated execution.
Core components
- Tool Bridge (MCP): Discovery & registration of tools
- Schema Explorer: Samples DBs, infers FKs, annotates PII
- Planner: Multi‑step typed plans (read→transform→write)
- Executor: Policy checks, approval prompts, rollbacks
- Telemetry: Step traces, spans, metrics for SLOs
Supported backends
PostgreSQL / MySQL
BigQuery / Snowflake
MongoDB / Redis
S3 / GCS (Parquet/CSV)
Notion / Confluence
HTTP/GraphQL APIs
Capabilities
What agents can do
Discover
Catalog schemas, detect joins, sensitive fields.
Synthesize
Generate queries, datasets, dashboards.
Simulate
Dry‑run mutations with rollback plans.
Node Retrieval +
Node Relationships
Node Relationships
Smart Node Retrieval
Neural Voyager leverages advanced graph-based algorithms to retrieve relevant nodes swiftly, allowing users to access precise information from complex, interconnected datasets
Dynamic Node Relationships
Maps and visualizes relationships between nodes to reveal the connections and patterns within datasets. This feature is particularly valuable for understanding data context, uncovering trends, and enhancing decision-making processes
Relationship Mapping for Insightful Analysis
By connecting relevant data points, Neural Voyager highlights correlations and dependencies that would otherwise remain hidden, providing a comprehensive view of the data landscape
Protocols
MCP tools and typed plans
Databases + MCP Protocols IV — DB exploration & ACID‑aware mutations.
MCP tool manifest
{
"name": "db.explorer",
"tools": [
{ "name": "schemas.list" },
{ "name": "tables.describe" },
{ "name": "query.run", "readonly": true },
{ "name": "mutation.plan" }
]
}Typed plan structure
type Plan = {
id: string,
soi: 'Private'|'Social'|'Public',
steps: [read|transform|write],
approvals?: { required: boolean, roles: string[] }
}Vector Database for
Indexing Relative Data
Indexing Relative Data
Efficient Vector-Based Indexing
Neural Voyager’s vector database indexes data based on contextual similarity, enabling rapid retrieval of relevant information. This indexing method ensures that related data is grouped and accessible, improving search efficiency and data relevance
Contextual Data Retrieval
The vector database allows for a high level of accuracy in data retrieval, ensuring that similar data points are indexed together and surfaced based on user queries
Scalable and Real-Time Access
Optimized for high-speed, real-time access, the vector database supports both small-scale operations and extensive enterprise-level datasets
Security
SoI‑aware safety & governance
Private/Social/Public controls applied per data source and action.
Least privilege
- Readonly by default
- Column & row‑level policies
- Scoped credentials
Approvals
- Risk‑tiered with human‑in‑the‑loop
- Dry‑run impact reports
- SOAR playbooks
Observability
- Trace steps with spans/metrics
- Record provenance
- Export to SIEM
Modularized Solution
Surfacing over a decade of spatial computing IP
Neural Voyager powers real-time intelligence and optimized performance for organizations requiring reliable, contextual data solutions, enabling impactful insights across industries.
Explore NV works with eVa to codify and secure data provenance
Explore NV works with eVa to codify and secure data provenance
Examples
Example agent journeys
Analytics Read
goal: "Explain revenue dip"
plan:
- read: SELECT * FROM revenue WHERE quarter='Q2'
- transform(sql): WITH ...
- synthesize: dashboard
soi: Social
approvals: noneSafe Write
goal: "Fix malformed emails"
plan:
- discover: schema
- simulate: UPDATE ...
- approval: owner + SOC
- write: UPDATE ...
soi: Private
approvals: requiredEmbedded Models for
In-Context Processing
In-Context Processing
Built-In Model Embeddings
Embedded models within Neural Voyager enable the platform to perform in-context data processing, extracting meaningful insights and adapting to real-time user inputs
Adaptable Model Layers
The embedded models can be tailored to various data types and user needs, enhancing the platform’s adaptability across different applications
In-Context Data Interpretation
These models process data within its unique context, ensuring that the information delivered is relevant, actionable, and reliable for users in both high-stakes and day-to-day scenarios
API
Agent & Tooling API (preview)
HTTP+JSON; MCP manifests for tools.
Create plan
POST /v1/voyager/plans { goal: "find churn", soi: "Social" }Execute plan
POST /v1/voyager/plans/{id}/execute { dryRun: true }Load Balancing and
Parsing Between LLMs
Parsing Between LLMs
Intelligent Load Balancer
Neural Voyager functions as a load balancer between large language models (LLMs), managing requests and distributing tasks to optimize performance and resource usage
Efficient Parsing Engine
Acts as a parser, breaking down complex queries and routing them to the appropriate LLM or model, ensuring accuracy and reducing processing time
Optimized LLM Interoperability
By balancing and parsing requests between LLMs, Neural Voyager prevents overload, reduces latency, and ensures that each request is handled by the best-suited model for the task
Get started
Pilot Neural Voyager
Bring your database and a problem. We'll wire MCP tools, define policies, and run a safe agent pilot in days.
XRDNA, MoE, Map of Everything, eVa, Sphere of Influence, and Neural Voyager are all registered trademarks for XRDNA Inc
2025 XRDNA, Inc. All Rights Reserved.
2025 XRDNA, Inc. All Rights Reserved.