Nikhil-Mukund/marvel

MARVEL is a locally deployable, open-source scientific assistant for domain-aware QA. Fast path + DeepSearch (RAG+MCTS) explores subqueries, allocates compute, and maintains an evidence ledger. Demonstrated for astrophysics and LIGO detector operations. Runs on authenticated networks; keeps data on-prem.

19
/ 100
Experimental
No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Python

License

Apache-2.0

Category

pdf-rag-qa-systems

Last pushed

Feb 05, 2026

Commits (30d)

0

GitHub
PDF RAG QA Systems · 118 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/Nikhil-Mukund/marvel"

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

Higher-rated alternatives

Future-House/paper-qa

High accuracy RAG for answering questions from scientific documents with citations

77

weiwill88/Local_Pdf_Chat_RAG

🧠 纯原生 Python 实现的 RAG 框架 | FAISS + BM25 混合检索 | 支持 Ollama / SiliconFlow | 适合新手入门学习

58

shubham0204/OnDevice-RAG-Android

A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android

47

dev-it-with-me/RagUltimateAdvisor

A complete Retrieval-Augmented Generation (RAG) application that demonstrates modern AI...

41

EarthlyAlien/Document-Assistant

RAG based Document Assistant for Search

40

Explore RAG Tools

All categories Trending RAG directory Insights