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

LLaMP helps materials scientists, chemists, and researchers quickly get reliable answers about material properties and structures. It takes your natural language questions and retrieves high-fidelity information from the Materials Project database. This reduces the risk of incorrect data (hallucinations) that can occur with general AI tools, providing accurate insights for your research and development.

Use this if you need to access and synthesize detailed materials informatics from large databases without sifting through extensive documentation or risking factual errors.

Not ideal if your research focuses on areas outside of materials science or does not rely on the Materials Project database for its core data.

materials-science materials-informatics chemistry material-property-prediction materials-discovery
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.