Awesome GitHub RepositoriesMultimodal Data Extractors

LightRAG is a graph-based retrieval framework designed to build retrieval-augmented generation pipelines. It structures unstructured text into knowledge graphs, enabling multi-hop reasoning and complex query synthesis across large document collections. By integrating dense vector embeddings with structured knowledge graphs, the system facilitates both similarity-based and relationship-aware information retrieval. The framework distinguishes itself through a dual-level retrieval strategy that combines low-level keyword matching with high-level semantic graph traversal to capture both specific

Supermemory is an artificial intelligence memory management platform designed to provide autonomous agents with persistent, long-term knowledge bases. It functions as a centralized repository that synchronizes multimodal data, enabling agents to maintain context and historical information across complex, multi-session workflows. By serving as a knowledge graph engine and vector database orchestrator, the platform ensures that information remains accessible and relevant for automated tasks. The system distinguishes itself through its hybrid indexing approach, which combines vector similarity s

RAG-Anything is a retrieval-augmented generation framework designed to index diverse document formats and perform semantic search using local machine learning models. It functions as a local multimodal data processor, extracting and organizing information from various file types into a unified knowledge base to facilitate private document analysis. The system distinguishes itself through its high-throughput ingestion engine, which processes large batches of documents into searchable vector embeddings. By executing machine learning models directly on local hardware, the framework ensures that

Podcastfy is an AI content-to-podcast generator that converts text, URLs, PDFs, images, and videos into conversational audio podcasts. It integrates with over 100 language models for transcript creation and multiple text-to-speech engines for audio output, with support for customizable dialogue style and optional local transcript generation for privacy. The project distinguishes itself through a flexible architecture that decouples job submission from result retrieval via asynchronous polling, normalizes heterogeneous inputs into uniform text, and routes content through pluggable LLM and TTS