LightRAG
The tool indexes documents into both a vector store and a graph of entities and relationships, then queries both at retrieval time — so a…
RAG frameworks and libraries (LlamaIndex, Haystack).
The tool indexes documents into both a vector store and a graph of entities and relationships, then queries both at retrieval time — so a…
The platform connects to SharePoint and company documents, runs retrieval-augmented generation with citations, and lets teams deploy…
Empirical addresses this by sitting between your AI tools and your projects as a persistent memory layer, capturing context once and making…
PixelRAG is an open-source retrieval framework that indexes document pages as images and searches over them using vision-language models…
The project implements a full memory lifecycle — typed capture, policy evaluation before storage or retrieval, hybrid retrieval combining…
ArXiv Scholar is an open-source RAG infrastructure that indexes roughly 5,600 curated AI engineering papers from arXiv and exposes them…
The server stores, retrieves, and versions memories using local ChromaDB, so context survives across sessions without touching any cloud…
The library plugs into vLLM or TGI backends and stores KV cache tensors so that overlapping prompt prefixes — system prompts, document…
The library pairs a GraphRAG implementation with a Vocabulary system: a shared, schema-enforced dictionary of node types, relationship…
The system fuses live satellite vegetation indices, rainfall anomaly data, and WFP food security indicators, then routes that combined…