hummat/paperpipe

Extract equations and context from research papers for LLM coding assistants (arXiv, LaTeX, RAG)

43
/ 100
Emerging

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.

Maintenance 13 / 25
Adoption 4 / 25
Maturity 18 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

MIT

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.