OASiS
Active·★ 29·MIT·Updated 2026-10-15
OASiS is an agentic simulation system that empowers AI language models to interact with eight professional finite-element and multiphysics codes via a unified interface. It automates problem description, solver selection, input generation, simulation execution, result verification, and outcome visualization, leveraging curated knowledge to ensure accuracy and efficiency.
#AI Agent#Multiphysics Simulation#Finite Element Method#Scientific Computing#Solver Orchestration#Code Coupling#LLM Integration
01
Features
01Operate eight professional FEM and multiphysics codes via a common interface.
02Automate simulation workflow: problem description, solver selection, input generation, execution, and verification.
03Support cross-code and multi-paradigm coupling, including preCICE integration.
04Enable AI agents to generate meshes and visualize simulation outcomes.
05Allow agent-driven solver source code modification, rebuilding, and testing for feature extension.
02
Compatibility
Python
Runtime
Verified via docs
AI Models
Inference
Verified via docs
Model Context Protocol (MCP)
Protocol
Verified via docs
LangGraph
Framework
Verified via docs
preCICE
Coupling Library
Verified via docs
Linux
OS
Verified via docs
03
Quick start
1
$ git clone https://github.com/Hereon-InstituteMS/OASiS.git
2
$ cd OASiS
3
$ python3 -m venv .venv
4
$ source .venv/bin/activate
5
$ pip install -e .
6
$ pip install scikit-fem
04
Use cases
↳Simulating a wide range of physics problems including PDEs, solid mechanics, flow, and electromagnetics.
↳Performing complex multi-physics and multi-code coupling simulations.
↳Automating mesh generation, result visualization, and convergence studies.
↳Enabling AI models to develop, modify, and test new features for simulation solvers.
↳Verifying simulation results against analytical solutions or established benchmarks.
05
Alternatives
build-world★ 104
Build interactive 3D worlds with high-quality assets from Thrixel and your AI agent of choice.
madcop★ 25
MadCop — local-first AI agent desktop workstation (v0.9). Multi-model chat, tool-use, MCP servers, 12 workflow modes, knowledge base, AI design tool, persistent workspace.
nac★ 284
Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.
Ageniti★ 31
A standard SDK for building agent-facing apps across MCP, CLI, React, and AI tool stacks.
Comments
Log in to leave a comment
No comments yet. Be the first!