Awesome Ai Agents 2026
Section: RAG and Knowledge Bases · Cloud-native vector DB. Billion-scale.
Entry
Appears in 14 awesome lists
Milvus is a cloud-native, open-source vector database built to manage embedding vectors generated by machine learning models and neural networks.
Section: RAG and Knowledge Bases · Cloud-native vector DB. Billion-scale.
Section: Vector Databases · open-source vector database for scalable similarity search.
Section: Databases · Vector database for scalable similarity search and AI applications.
Section: Vector Databases (RAG) · Milvus is an open-source vector database built to power embedding similarity search and AI applications.
Section: Databases Implemented in Go · Milvus is a vector database for embedding management, analytics and search.
Section: Go中实现的数据库 · star:42514 Milvus是一个矢量数据库,用于嵌入管理、分析和搜索。
Section: Vector search · Vector database for scalable similarity search and AI applications.
Section: Data Management · An open source embedding vector similarity search engine powered by Faiss, NMSLIB and Annoy.
Section: 5. Retrieval-Augmented Generation (RAG) & Knowledge · Scalable cloud-native vector database.
Section: vector-database · 一个云原生向量数据库,为下一代人工智能应用提供存储
Section: Data Storage Optimisation · Milvus is a cloud-native, open-source vector database built to manage embedding vectors generated by machine learning models and neural networks.
Section: Standalone Service
Section: 数据库 · 向量数据库
Section: Other · Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
The most-deployed memory layer for AI agents — drop-in add/search/update/delete fact storage with LLM-extracted long-term / short-term / semantic memory: automatic fact consolidation (dedup, contradiction resolution, decay) so agents keep "context that persists" without context bloat;…
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
An open-source embedding database for building AI applications with semantic search.
AI-native database built for LLM applications with incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text. Powers RAGFlow's document engine. Apache 2.0 licensed.
An open source vector database that stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance and scalability of a cloud-native database, all accessible through GraphQL, REST, and various language clients.