CodeNinja today released multiple open reference architectures through CodeNinja Atoms for deploying sovereign physical AI. The industry blueprints provide complete system designs for real operations in energy, oil and gas, ports, rail, manufacturing, heavy industry, aviation, and agriculture across the United States, Saudi Arabia, and Pakistan.
Each architecture publishes the design logic behind deployment, including what to sense, where each model runs, the object model that connects an operation’s existing systems, the open-weight models and hardware required, three-year costs, and the named person who approves every action. Released under the Creative Commons Attribution 4.0 (CC 4.0) International license, the library is free for engineers and enterprises to study, reuse, and adapt.
Open Is How Ownership Starts
Many organizations can use AI without retaining the design logic, model choices, object model or operating knowledge behind it. When those elements stay external, the organization cannot independently inspect, adapt or extend the system it depends on.
Atoms puts each of those elements in the open. The reference architecture makes the design inspectable. The published object model makes the structure of the operation reusable. The model, hardware and cost choices make every trade-off visible. The open license lets any team adapt the design to its own operation and keep what it builds.
Muhammad Umar Bilal, Co-Founder of CodeNinja, said:
An organization cannot govern a system it cannot see. By publishing the design, the object model and the data behind each architecture, we let engineers and operators inspect how these systems work, adapt them to their own operations and build them on infrastructure they control.
Design Expertise on Demand
The hardest part of physical AI is rarely the model. It is the design, and the expertise to get it right is scarce and often sits outside the organization that needs it.
Praxis closes that gap. It is a blueprint engine for physical AI, grounded in published research and industry standards. Through a recursive learning loop, every design, benchmark run and engineer’s correction is written back to memory and applied to the next requirement, with each loop scored on our public benchmark. Engineers get a reasoning base for systems where domain expertise is scarce.
- A single operational requirement goes in, written in the operator’s own words.
- A complete system design comes out, from sensing and model placement to the object model, hardware, three-year cost and the approvals each action requires.
- Every choice arrives with the reason behind it, and a live simulation shows the operation running on the design before anything is built.
Praxis Leads the Latest CodeNinja Physical AI Design Benchmark
The Physical AI Design Index (PADI) is CodeNinja’s own benchmark. It gives Praxis and frontier AI on its own the same short requirement and scores both designs against the same checks, on fresh tasks across 13 industries. In Loop 22, a blind evaluation on seven unseen tasks run on 16 October, Praxis passed 48.5 percent of checks against 28.4 percent for frontier AI and led on all seven. Earlier loops ran on different tasks and show the trend rather than a like-for-like comparison. Every result is published by industry and by loop, and the scores remain far from saturated.
Every Design Is Yours to Build On
Explore all reference architectures at codeatoms.ai.
The full library is also available as the open dataset CodeNinjatools/vertical-driven-architectures on Hugging Face, with tables for designs, object models, model choices, cost lines and full text, and every paper carries its own DOI on Zenodo. Engineers can apply for Praxis developer access at codeatoms.ai, and organizations that want a physical AI system built for their own operation can contact CodeNinja.
Muhammad Umar Bilal, Co-Founder of CodeNinja, said:
We want every engineer to build on these designs and every enterprise to see exactly how a system like theirs is made. When an operator is ready for one of its own, our forward deployed engineers build it inside its walls.
