pathwaycom/llm-app
Ready-to-run cloud templates for building real-time RAG, AI pipelines, and enterprise search applications that synchronize with various live data sources.
Awesome Infra for AI › Vector Databases & Retrieval Infrastructure
orneryd/NornicDB
NornicDB is a high-performance distributed database that uniquely combines graph, vector, and temporal MVCC capabilities, specifically engineered for AI-native applications. It leverages Neo4j's Bolt and Cypher protocols for graph queries and Qdrant's gRPC for vector operations, allowing seamless migration and interoperability. The database is built for workloads requiring graph traversal, semantic search, and historical data truth within a single system, making it ideal for knowledge systems, AI agent memory, and Graph-RAG (Retrieval-Augmented Generation). Key features include first-class support for vector search, memory decay, auto-relationships, and hardware acceleration (CUDA, Metal, Vulkan) for high-throughput graph and semantic workloads. It offers snapshot isolation for transactional integrity and explicit historical reads via MVCC, providing a consistent view of the graph at any point in time. NornicDB aims to consolidate complex AI stacks by offering a unified platform for tasks typically spread across multiple databases like Neo4j and Qdrant, streamlining deployment patterns for agent and Graph-RAG systems, as well as translation and evaluation workflows. It supports various deployment options including full images (with models), bring-your-own-model images, and headless API-only setups.
https://github.com/orneryd/NornicDB
Also in Vector Databases & Retrieval Infrastructure
run-llama/llama_index
LlamaIndex is an open-source data framework for building LLM applications by connecting custom data sources to large language models, focusing on data ingestion, indexing, and retrieval augmented g...
milvus-io/milvus
Milvus is a high-performance, cloud-native vector database designed for scalable vector Approximate Nearest Neighbor (ANN) search, efficiently organizing and searching vast amounts of unstructured ...
VectifyAI/PageIndex
PageIndex is a vectorless, reasoning-based RAG system that builds hierarchical tree indexes from documents and uses LLMs to reason over them for context-aware retrieval.
qdrant/qdrant
Qdrant is an open-source, high-performance vector similarity search engine and vector database designed specifically for AI applications, enabling fast storage, search, and management of vectors wi...
Tencent/WeKnora
WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval, and autonomous reasoning, featuring RAG, ReAct agents, and an auto-maintaining ...
topoteretes/cognee
Cognee is an open-source AI memory platform that provides AI agents with persistent long-term memory through a self-hosted knowledge graph, combining vector embeddings and graph reasoning.
RyanCodrai/turbovec
TurboVec is a Rust-based approximate nearest neighbor (ANN) vector index with Python bindings, built on Google Research's TurboQuant algorithm for efficient, memory-optimized vector similarity search.