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
unum-cloud/USearch
USearch is an open-source, high-performance similarity search and clustering engine designed for vectors and arbitrary objects. It offers a faster and more compact alternative to established solutions like FAISS, primarily by focusing on a single-file C++11 header library with broad language compatibility (C++, Python, JavaScript, Java, Rust, C, Objective-C, Swift, C#, Go, Wolfram). The engine implements a highly optimized Hierarchical Navigable Small World (HNSW) algorithm, featuring SIMD acceleration, JIT compilation for user-defined metrics, and support for various data types including half-precision and quarter-precision for memory efficiency. Key capabilities of USearch include: fast indexing and search with significant performance improvements over FAISS, the ability to view large indexes directly from disk without full RAM loading, heterogeneous lookups, renaming/relabeling, and on-the-fly deletions. It also supports binary Tanimoto and Sorensen coefficients for specialized applications in genomics and chemistry, and offers near-real-time clustering and sub-clustering. The project emphasizes portability, minimal dependencies, and a small footprint, making it suitable for deployment in diverse environments including mobile and WebAssembly. Its integrations with databases like ClickHouse and DuckDB highlight its utility as a core component for vector similarity search and retrieval infrastructure within AI/ML serving stacks.
https://github.com/unum-cloud/USearch
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.