Developers
Hyper. The architecture under everything CodeNinja builds.
Hyper is the architecture CodeNinja's platforms are built on. Praxis designs a physical AI system. Hyper Ontology structures the operation's context. Hyper Pragma runs agents inside the enterprise boundary. Hyper Engram keeps the decision memory every run reads before it acts. Hyper Noesis opens the models an organization owns so their reasoning can be inspected. CodeNinja Atoms, the reference architectures on this site, is the first thing built on it. This is where developers start.
Capabilities
Five platforms on one architecture. Each does one thing in the life of an operation's context, and each is built on Hyper.
Praxis
Praxis turns an operator's requirement into a complete design for physical AI, with every claim on a record and a person on every write.
Build with it: A complete system design for one operation: what to sense, where each model runs, the object model, the hardware, the three-year cost and who approves every action.
Beta, open to outside engineersHyper Ontology
Hyper Ontology holds the governed model of the organization. It imports the object model a Praxis design publishes and stands it up as a living system over the operator's own systems of record.
Build with it: A living ontology over an operator's existing systems: typed objects, typed links, and actions that sense, decide, act and learn.
How it becomes livingPackage format
Beta, a small number of teamsHyper Pragma
Hyper Pragma is agent execution inside the enterprise boundary, on models the organization can change without losing what was built.
Build with it: Agents that work on the operator's own hardware, on open-weight models the operator can swap, with the context carried across the swap.
Used in house, not yet openHyper Engram
Hyper Engram is decision memory each run reads before it acts: the record of what was decided, by whom, and what worked.
Build with it: Systems that improve run over run because every run starts by reading what earlier runs and people recorded.
Used in house, not yet openHyper Noesis
Hyper Noesis opens models the organization owns so their reasoning can be inspected, rather than taken on trust.
Build with it: Verification of a model's behaviour before it is trusted with an operation, and after every change of model.
Used in house, not yet openGetting started
Four ways in, all open today. Pick the one that matches what you are building.
Design a system on Praxis
Unlock free access, paste a requirement, and Praxis returns a complete system design. Every account is approved by CodeNinja, usually within a day.
Give your coding agent every design
The MCP server lists, searches and reads the published designs: object models, model and hardware registers, cost lines and full papers.
claude mcp add codeninja-research -- uvx --from "git+https://github.com/muhammadumar89/codeninja-research#subdirectory=mcp-server" codeninja-research-mcpLoad an object model
The loader reads any published hyper-ontology/1 package, validates it, walks its typed links and converts it to Mermaid, Cypher or JSON-LD.
pip install "git+https://github.com/muhammadumar89/codeninja-research#subdirectory=hyper-ontology-py"
hyper-ontology show port-digital-twin-us
hyper-ontology cypher port-digital-twin-us > load.cypherQuery the dataset
Every design is a row in five tables: designs, objects, models, costs and full text. One load gives you all of them.
from datasets import load_dataset
objects = load_dataset("CodeNinjatools/vertical-driven-architectures", "objects", split="train")
print(objects.filter(lambda r: r["kind"] == "event")["label"])Reference
The formats and tools, documented from the repository itself.
The hyper-ontology/1 package format
What every published object model contains, the rules it follows, and what an agent does with it.
The hyper-ontology loader
Load, validate, traverse and convert packages from the command line or Python.
The MCP server
Five tools that give a coding agent every design: list, get, read, find, and where the designs come from.
The Vertical-Driven Architectures dataset
Five tables, one row per design, object, model choice or cost line; monthly DOI snapshots.
Samples
Every published design is a worked example: a complete system built on Hyper for one real operation, with its object model as a package you can load. All of them in one table: sovereign AI reference architectures; every object model: industrial ontology examples.
agriculture and earth observation
Field LedgerPakistan · 12 objects · DOI 10.5281/zenodo.23186671BaselineUnited States · 16 objects · DOI 10.5281/zenodo.23186673Fodder WatchSaudi Arabia · 14 objects · DOI 10.5281/zenodo.23186675A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanPakistan · 16 objects · DOI 10.5281/zenodo.24048587aviation and aerospace manufacturing
Hangar Form CellUnited States · 14 objects · DOI 10.5281/zenodo.23308095Physical AI System Design for Composite Part Inspection in an Aviation MRO in Saudi ArabiaSaudi Arabia · 16 objects · DOI 10.5281/zenodo.24048561Industrial AI Reference Architecture for an Engine MRO Shop Floor in the United StatesUnited States · 15 objects · DOI 10.5281/zenodo.24048571discrete manufacturing and automotive
Pit Camera WatchUnited States · 15 objects · DOI 10.5281/zenodo.23296077Depot Operating Object ModelUnited States · 14 objects · DOI 10.5281/zenodo.23570177Physical AI System Design for Weld and Assembly Quality in a Vehicle Plant in PakistanPakistan · 16 objects · DOI 10.5281/zenodo.24048589energy and utilities
Grid Context WatchUnited States · 14 objects · DOI 10.5281/zenodo.23157957Reliability AtlasSaudi Arabia · 13 objects · DOI 10.5281/zenodo.23157965Feeder FirewatchUnited States · 14 objects · DOI 10.5281/zenodo.23159328Turbine Island WatchPakistan · 10 objects · DOI 10.5281/zenodo.23365092Sovereign AI Architecture for a Grid Control Room in Saudi ArabiaSaudi Arabia · 16 objects · DOI 10.5281/zenodo.23889768Industrial Data Ontology for a Water Utility in the United StatesUnited States · 16 objects · DOI 10.5281/zenodo.23889772Sovereign AI Architecture for Distribution Loss and Theft Reduction in PakistanPakistan · 15 objects · DOI 10.5281/zenodo.24048559A Self-Improving AI System for OT Vulnerability Management at a Utility in the United StatesUnited States · 16 objects · DOI 10.5281/zenodo.24048567heavy industry and construction
Structure Phase WatchSaudi Arabia · 15 objects · DOI 10.5281/zenodo.23126448Steel Count LedgerPakistan · 14 objects · DOI 10.5281/zenodo.23126563Factory Fire WatchSaudi Arabia · 14 objects · DOI 10.5281/zenodo.23126565A Self-Improving AI System for Cement Kiln Control in Saudi ArabiaSaudi Arabia · 16 objects · DOI 10.5281/zenodo.24048545Industrial AI Reference Architecture for Fertilizer Plant Reliability in PakistanPakistan · 14 objects · DOI 10.5281/zenodo.24048577maritime and ports
Port TwinUnited States · 13 objects · DOI 10.5281/zenodo.23126431Terminal PulseUnited States · 12 objects · DOI 10.5281/zenodo.23159331Port Drone WatchGermany · 15 objects · DOI 10.5281/zenodo.23635729Industrial Ontology ExamplesSaudi Arabia · 16 objects · DOI 10.5281/zenodo.24048525mining
Industrial AI for an Open Pit Mine Haul Fleet in Saudi ArabiaSaudi Arabia · 16 objects · DOI 10.5281/zenodo.23889774Industrial AI Reference Architecture for Tailings Storage Facility Monitoring in the United StatesUnited States · 15 objects · DOI 10.5281/zenodo.24048569Sovereign AI Reference Architectures for a Remote Mine on a Satellite Link in PakistanPakistan · 15 objects · DOI 10.5281/zenodo.24048581oil and gas
Sovereign HSE WatchPakistan · 12 objects · DOI 10.5281/zenodo.23119714Loop Integrity WatchPakistan · 15 objects · DOI 10.5281/zenodo.23157967Corridor GuardPakistan · 15 objects · DOI 10.5281/zenodo.23308093Pipeline Integrity WatchUnited States · 14 objects · DOI 10.5281/zenodo.23556374rail and transportation
Consist WatchUnited States · 14 objects · DOI 10.5281/zenodo.23365118Wayside Trend WatchUnited States · 14 objects · DOI 10.5281/zenodo.23556421Sovereign AI Reference Architectures for Passenger Rail Fleet Maintenance in Saudi ArabiaSaudi Arabia · 14 objects · DOI 10.5281/zenodo.24048549semiconductors
Silicon LedgerSaudi Arabia · 16 objects · DOI 10.5281/zenodo.23693146Physical AI System Design for Wafer Defect Inspection in the United StatesUnited States · 16 objects · DOI 10.5281/zenodo.23889770supply chain and logistics
Industrial Data Ontology for a Cold Chain From Plant to Store in the United StatesUnited States · 16 objects · DOI 10.5281/zenodo.24048543Sovereign AI Architecture for a Freight Corridor and Customs Clearance in Saudi ArabiaSaudi Arabia · 15 objects · DOI 10.5281/zenodo.24048557A Self-Improving AI System for Carrier Exception Handling in the United StatesUnited States · 16 objects · DOI 10.5281/zenodo.24048585warehousing and intralogistics
Warehouse Twin CommandUnited States · 14 objects · DOI 10.5281/zenodo.23556416Physical AI System Design for a Mobile Robot Fulfilment Centre in Saudi ArabiaSaudi Arabia · 15 objects · DOI 10.5281/zenodo.24048579Platform updates
What changed in the format, the loader, the MCP server and the dataset, from the repository's history. All updates
- DOIs for the sixteen 8 Nov designs (10.5281/zenodo.24048525 to 24048589): objects.json, READMEs, web editions, dataset rows and card
- Publish sixteen reference architectures from the twenty designs handoff (ep40, 8 Nov 2026)
- Dataset November 2026 release, DOI 10.5281/zenodo.23889945; four new designs in the dataset card
- Publish four reference architectures and one requirement post (ep34 SEO five)
- Publish Silicon Ledger (semiconductors, Saudi Arabia), DOI 10.5281/zenodo.23693146
- Ep24: dataset card lists Port Drone Watch
- Publish Port Drone Watch (maritime and ports, Germany), DOI 10.5281/zenodo.23635729
- Ep24: dataset card lists the Depot Operating Object Model
Community
Questions, answers and what people build live in the repository's discussions. A GitHub account is all it takes.
- Announcements
What changed, release by release. - Q&A
Ask about a design, a package, the loader or the MCP server. - Show and tell
What you built on Hyper: an ontology over your systems, an agent, a tool. - Ideas
What the next design, format or tool should be.
Latest threads
- Start the first threadQ&A · open to everyone with a GitHub account
Also: the engineering blog and its feed, issues for bugs in the loader or the server, and the Hugging Face organization for every dataset and Space.