Talorik OS
Decision software that runs on your network. A live model of how the operation actually works.
What sits under the desk
Talorik OS is the layer that sits under Inputless Analytics: ingest, ontology, graph, and the decision trail. Like an operating system, other work runs on it. Unlike a BI suite, it does not wait for someone to write a report.
It keeps a working model of the operation and hands the desk a shortlist. A person still signs the call.
Talk to usData Ingestion Layer
Feeds from the systems you already run. Continuous ingest. You are not standing up a new ETL program to get started.
Cognitive Substrate
A live map of how your organization classifies events and what it usually does next. Relationships, cause, and context, kept current.
Operating System Core
Talorik OS coordinates ingest, the substrate, and the decision layer. The runtime under Inputless Analytics.
Decision Layer
Ranked next steps with a trail. Anomalies and risks show up without someone opening a blank dashboard.
Technical Architecture
Frontend Layer
TypeScript SDK for real-time event capture and on-device cognitive processing.
- • @inputless/tracker - Event collection
- • @inputless/sdk-cognitive - On-device intelligence
- • @inputless/context - Pattern detection
- • @inputless/dispatcher - Signal routing
Backend Layer
Python services for AI/ML processing, genetic algorithms, and pattern evolution.
- • inputless-engines - Mutation & reasoning
- • inputless-models - Pattern recognition
- • inputless-graph - Inputless DB integration
- • inputless-ingestion - Document processing
Graph Database
Inputless DB stores events, relationships, and patterns as a kinetic graph structure.
A shared vocabulary
Objects, links, and words that mean the same thing on every desk.
Same objects, same names
The Cognitive Substrate holds the ontology: what an event is, what an action is, how they relate, and how a decision is recorded. A data model desks can argue about in the open.
When two systems use the same types, you stop translating. Context survives a hand-off. A later recommendation can reuse a pattern instead of inventing a new one.
Why the ontology exists
Fewer adapters
Shared types mean less glue between systems. You still integrate; you do not invent a new dictionary each time.
You can explain it
If two desks use the same words, a recommendation can be walked through. That is the audit path.
Reuse the pattern
A relationship learned on one line can apply on another, if the types match. Duplicate models are waste.
It can change
You add domain types as the operation changes. The core types stay stable so old trails still read.
Where we operate
Intelligence for desks where delay is expensive
Energy
Planetary-scale operations and grid intelligence
Model generation, transmission, and market signals in one continuous view so teams see imbalance and risk before they cascade.
Energy