Repository Index

A lightweight, lightning-fast, in-process vector database

• rag
• agent-skills
• embedded
• faiss

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

• c-plus-plus
• python
• nearest-neighbor-search
• locality-sensitive-hashing

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

• ai
• faiss
• langchain
• llama-index

Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

• bolt
• cypher
• database
• enterprise-solutions

Swift database - fast, simple and lightweight (iOS, macOS)

• ios
• database
• edge
• embedded

A c++ toolbox of locality-sensitive hashing (LSH), provides several popular LSH algorithms, also support python and matlab.