Import a STEP file, build CSG bodies, mesh with Gmsh, solve with FEniCSx / MFEM / PhysicsNemo backends — all without leaving your browser. Every action is recorded as a Python journal you can replay or hand to the built-in AI assistant.
OCCT for geometry. Gmsh for meshing. FEniCSx and MFEM for multiphysics. Wired together so the cycle from STEP-in to simulation-out is seamless.
Browser-native CSG modeling. Boolean operations on STEP bodies with stable entity IDs for simulation-ready geometry.
Gmsh-powered meshing with hex-dominant, transfinite, and Delaunay algorithms. Automatic refinement based on curvature.
FEniCSx and MFEM backends for structural, thermal, and CFD simulations. Supports linear/nonlinear solvers with complex boundary conditions.
Differentiable surrogate modeling powered by PhysicsNemo. Fast, predictive analysis for design space exploration.
Click your way through, replay a Python journal, or ask the AI. All three paths produce identical state.
Every action you take is also written to a journal entry — so exploration is automatically a recording. No "save script" step, no separate macro recorder mode.
Saved as plain Python with stable body_0 / body_1 references — readable, diffable, parametrisable. session.csg_transform("body_2", "rotate", {...}).
"Make a 20mm box with a 5mm cylindrical hole." "Mesh with HXT at size factor 0.5." The assistant emits tool calls that drive the same DOM handlers as Manual UI.
Click faces in the viewport. Group the ones that should share a boundary condition. Assign a fixed support, a traction, a pressure, or a temperature. Face tags survive across CAD edits and mesh rebuilds.
Compute credits for only what you use.
