A
Automat
Autonomous feature engineering for materials science via LLM-driven genetic programming
Open SourceFree
About
Academic research framework from Trinity College Dublin that uses coding agents to automatically design compositional descriptors for materials science. Goes beyond traditional AutoML by combining LLM-based code generation with genetic programming to automate feature engineering rather than just hyperparameter tuning. Demonstrates autonomous research capabilities where agents iteratively improve material property predictions by discovering novel feature representations.
Details
| Language | |
| Patterns |
Tags
coding-agentautonomousframeworkopen-sourcepythonevaluation
Quick Info
- Organization
- Trinity College Dublin
- Pricing
- open-source
- Free Tier
- Yes
- Updated
- May 16, 2026
Also in Frameworks
L
LangChain
Build context-aware reasoning applications with LLMs
OSSFree
LangChain AI
136.8K850.0K/wtoday469
A
AutoGen
Microsoft's framework for building multi-agent AI systems
OSSFree
Microsoft
58.1K4w ago445
C
CrewAI
Multi-agent orchestration framework for collaborative AI workflows
OSSFree
CrewAI Inc
51.5Ktoday296