{"repo":"NTU-Siqiang-Group/AsterVec","free":true,"listed":false,"github":"https://github.com/NTU-Siqiang-Group/AsterVec","clone":"git clone https://github.com/NTU-Siqiang-Group/AsterVec.git","description":"Embedded on-device vector database for AI agent memory and local RAG — disk-based HNSW in an LSM-tree, C++/Python, optimized for low memory footprint","language":"C++","stars":30,"topics":["ai-memory","approximate-nearest-neighbor-search","cpp","embedded-database","hnsw","lsm-tree","nearest-neighbor-search","on-device-ai","python","rag"],"license":"Apache-2.0","category":"ai-agents","readme_excerpt":"Memory-friendly vector engine for on-device AI memory. Quick Start · Why · How it works · Docs AsterVec is a vector search engine that keeps its index on disk and puts as little as possible in memory. RAM holds only a small navigation structure and caches, so an application can search millions of embeddings within a few hundred MB of memory. It is built for local AI agents and desktop RAG. At the heart of AsterVec is one architectural decision: on disk, the graph and the vectors are stored separately , because the two parts are updated and accessed in essentially different patterns. - Graph — edges churn in small, scattered writes, so they live in Aster, a graph-oriented LSM-tree that absorbs them out of place. - Vectors — they rarely change once written, so they live in packed pages built for bulk reads. Keeping the two apart is what makes updates cheap: a graph change writes only edges and never touches a vector page. Quick start Your data stays live — no index rebuilds: Why AsterVec - 🪶 Small memory, by design — RAM holds only the navigation structure and caches. You choose the memory budget, and it stays flat as your data grows. - 🔁 Live data — insert, update, and delete without ever rebuilding. - 🏷️ Filtered search — attach JSON metadata, query it Mongo-style. - 🔌 Runs inside your app — a thread-safe Python/C++ library that needs no separate service. An optional HTTP server is included for when you want one. Search speed Memory needed --- --- --- In-memory graph inde","default_branch":null,"files":null,"tree":[],"storefront":"/r/NTU-Siqiang-Group","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/NTU-Siqiang-Group/AsterVec/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}