mrta-rag is a locally-run, citation-aware research and teaching assistant built on RAG principles. It processes technical PDF documents to provide accurate answers with traceable citations. Designed for researchers, educators, and students who need a private, offline-capable assistant for deep technical material.
In the AI & ML space, mrta-rag takes a focused approach. It focuses on performing accurate, citation-grounded research and teaching assistance on technical PDF documents without relying on cloud services. mrta-rag is an open-source project aimed at researchers. The project is open source (MIT). mrta-rag is available on the command line.
sanya2025 builds and maintains mrta-rag, and it first shipped in 2026. The project is developed in the open on GitHub with 98 commits in the last 90 days. Key capabilities include PDF Analysis, Citation Awareness, and Local RAG.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match