0verL1nk/PaperSage
📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent workflows (ReAct/Plan-Act/RePlan), long-term memory, and traceable evidence. Built with LangChain + LangGraph + Streamlit.
Supports structured multi-agent team coordination through Leader-Teammate workflows with dependency-based todo scheduling and automatic protocol execution (A2A), alongside session-level query deduplication and project-scoped context management with episodic/semantic/procedural memory layers. Persists vector embeddings via Chroma with InMemoryVectorStore fallback, and instruments middleware for complexity-driven workflow routing that maintains structured evidence traces with chunk-level provenance (doc_uid, page_no, offset).
Stars
32
Forks
7
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/0verL1nk/PaperSage"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...
RapidFireAI/rapidfireai
RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning
WING-NUS/cs6101
The Web IR / NLP Group (WING)'s public reading group at the National University of Singapore.