hummat/paperpipe
Extract equations and context from research papers for LLM coding assistants (arXiv, LaTeX, RAG)
Maintains a local database of PDFs, extracted LaTeX source, and equation/summary markdown indexed by paper identifier. Integrates with RAG backends (PaperQA2, LEANN) for cross-paper semantic queries and exposes papers via MCP servers for direct integration into Claude Code and other LLM coding assistants. Supports batch imports from arXiv, URLs, Semantic Scholar, BibTeX, or title search, with hybrid FTS5/BM25 ranked search and grep-style queries across all extracted content.
Available on PyPI.
Stars
8
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/hummat/paperpipe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LearningCircuit/local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports...
NVIDIA-AI-Blueprints/rag
This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented...
hienhayho/rag-colls
Collection of recent advanced RAG techniques.
jeremiahbohr/literature-mapper
Transform academic PDFs into a Knowledge Graph with typed claims, temporal analysis,...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...