Here's what's new in our latest update:
You can now add interactive widgets directly from the dropdown in the canvas. The assistant will then insert a widget and enable you to adjust its properties interactively.
Here's what's new in our latest update:
With our new integration with Onshape by PTC, geometry, simulation, and Physics AI model development now live in one continuous loop:
You can access the integration directly from the Onshape app store.
Read the news to learn more.
You can now create tags automatically from selected surfaces in the in-app notebook viewer. Simply select the surfaces of interest, click on the three dots at the bottom right, and select Create Tag from Selected Surfaces.
Here's what's new in our latest update:
Clearer error handling
No more guessing where a timeout came from. When Mesh.wait()
or Simulation.wait()
times out, the SDK now raises a specific luminarycloud.exceptions.Timeout
. This removes the ambiguity of Python’s generic TimeoutError
and makes debugging much easier.
Direct access to project IDs
You can now grab a project_id
right from Geometry
, saving you extra steps and making project-specific workflows simpler.
Use your saved cameras everywhere
Cameras saved in the UI are now accessible through the SDK with vis.list_cameras
and vis.get_cameras
. That means you can quickly recreate the exact same views in your scripts that you set up visually in the app.
For full details, see the SDK release notes.
Here's what's new in our latest update:
You can now see where other editors are working within a project as it happens. This makes it easier to coordinate, avoid conflicts, and stay aligned while working together.
When another user is editing, their presence will be highlighted directly in the interface, so you’ll always know which part of the project they’re working on.
Each notebook now runs on its own dedicated kernel.
This eliminates the need to restart kernels when switching notebooks and allows you to open and work on multiple notebooks simultaneously—across tabs or sessions—without conflicts.
You can now export exactly what you see in the Results table.
When you choose to hide columns in the table, those columns will no longer appear in your exported data. This makes it easier to generate clean, focused exports without extra post-processing, ensuring that your downloaded results always match your on-screen view.
This release introduces significant updates to mesh creation and error handling, including breaking changes from v0.18.*.
Mesh generation is now asynchronous with updated deduplication behavior, the deprecated Project.create_mesh()
method has been removed, and a new DeadlineExceededError
exception type has been added.
For full details, see the SDK release notes.
Here's what's new in our latest update:
Added support for orthotropic conductivity in an arbitrary frame.
Note: temperature-dependence is not currently supported with orthotropic conductivity.
Here's what's new in our latest update:
Added support for specifying thickness and conductivity of interface materials between heat transfer zones.
You can now define pitch, roll, and yaw moments in the stability frame.
Here's what's new in our latest update:
When using the in-app notebook it's common to create images, CSVs, and other temporary files during the course of running a script. You now have the ability to download all temporary files from the notebook. Simply right-click on the file and select Download.
Here's what's new in our latest update:
You can now cycle through your last 100 queries using the Up and Down arrow keys when the chat box is selected.
You can now specify inlet flow direction using cylindrical coordinates—radial, tangential, and axial—making it easier to set up certain internal flow cases.
The assistant now supports creating, updating, and deleting volume reduction outputs, including force/moment, surface average, and residual outputs.
Here's what's new in our latest update:
Faster Results Loading with Local Render Data Caching
To improve performance, Luminary now caches visualization data files locally using your browser. This feature substantially improves project load times (up to 45x in some cases) when re-opening previously visited projects, as the data no longer needs to be downloaded. You can manage your cache size in My Account > Settings. The cached data is managed securely by your browser and not visible to other pages or your local filesystem.
AI Assistant: Expanded Output Support
The Assistant now supports creating, updating, and deleting a wider range of outputs — including force/moment, surface average, residual, and volume reduction. You can also modify reference values and stopping conditions directly through the assistant. (Note: Point probes, inner iteration data, and derived outputs aren't yet supported.)
Here's what's new in our latest update:
You can now share projects with Writer permissions. This allows multiple users within your organization to collaboratively edit projects in real time.
You can now ask the assistant to explain code directly from the hover toolbar within a notebook cell. Just hover and click Explain Code to get an instant breakdown of what’s happening.
You can now convert surface colors from your CAD file into Tags. This gives you a visual and flexible way to organize surfaces before importing into Luminary. To use it, right-click on Tags in the geometry tree and select Convert Colors to Tags.
The new Luminary Cloud MCP Server lets your AI agents in VSCode and Cursor connect directly to the Luminary platform. This enables them to write Luminary SDK code within your IDE.
Learn how to install the Luminary MCP server here.
Multi-Kernel History
You can now switch between continuous and discrete kernels without breaking model history. This unlocks a more fluid and intuitive workflow across geometry types.
This enhancement eliminates friction when transitioning between modeling and meshing workflows, while preserving traceability and flexibility.