The growing volume of scientific literature has made research-paper analysis increasingly time-consuming for students, researchers, and academicians. Tasks such as literature review generation, methodology understanding, research gap identification, citation formatting, and trend discovery often require substantial manual effort. To address these challenges, this paper presents ScholarForge AI, an open, multi-agent Retrieval-Augmented Generation (RAG) platform designed to automate research-paper analysis and transform scholarly documents into actionable research intelligence. The proposed system integrates Large Language Models (LLMs), LangGraph-based multi-agent orchestration, ChromaDB vector storage, a Neo4j knowledge graph, and Natural Language Processing (NLP) techniques to support intelligent document processing. Research papers in PDF format are processed using PyMuPDF and EasyOCR, then chunked and embedded with the BAAI/bge-small-en-v1.5 sentence transformer model for semantic retrieval. The platform includes specialized agents for literature review generation, methodology analysis, research gap detection, trend analysis, research idea generation, citation formatting, interactive question answering and difficulty prediction. In addition, a research difficulty predictor classifies papers as Easy, Medium, or Hard, while the knowledge graph visualizes relationships among papers, authors, keywords, methods, and topics. Experimental results show that ScholarForge AI improves the efficiency of literature survey preparation, supports accurate gap identification, and provides context-aware research recommendations. Built entirely on open-source technologies, the platform offers a scalable and accessible solution for academic research support.