MADA
Multi-agent framework for HPC-powered design workflows with automated experiment tracking
About
MADA (Multi-Agent Design Assistant) is a specialized framework from Lawrence Livermore National Laboratory that orchestrates multiple LLM-powered agents to handle complex design workflows on high-performance computing systems. It coordinates specialized agents for job management, experiment tracking, resource allocation, and automated design space exploration. Built for researchers and engineers working with computationally intensive design problems, MADA bridges the gap between AI agents and supercomputing infrastructure for scientific and engineering applications.
Details
| Language | |
| Patterns |
Tags
Quick Info
- Organization
- Lawrence Livermore National Laboratory
- Pricing
- open-source
- Free Tier
- Yes
- Updated
- Mar 13, 2026
Also in Frameworks
LangChain
Build context-aware reasoning applications with LLMs
AutoGen
Microsoft's framework for building multi-agent AI systems
CrewAI
Multi-agent orchestration framework for collaborative AI workflows