chiang-yuan/llamp

[EMNLP '25] A web app and Python API for multi-modal RAG framework to ground LLMs on high-fidelity materials informatics. An agentic materials scientist powered by @materialsproject, @langchain-ai, and @openai https://aclanthology.org/2025.emnlp-main.1280/

47
/ 100
Emerging

Implements hierarchical ReAct agents that recursively query the Materials Project API to retrieve structured materials data, reducing LLM hallucination through dynamic tool-use chains. The framework supports optional atomistic simulation workflows via ASE, Atomate2, and MACE, enabling computational validation alongside knowledge retrieval. Built as a modular LangChain extension with both Python API and Docker-based web interface (using Svelte frontend) for conversational access to materials informatics.

No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

89

Forks

14

Language

Jupyter Notebook

License

Last pushed

Nov 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/chiang-yuan/llamp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.