Embedchain

A MemAgent framework that can extrapolate to 3.5M context tokens, along with a training framework for RL training of any agent workflow.

A hyper-fast local vector database for use with LLM Agents, providing lightweight vector storage and similarity search capabilities for embedding as instant memory and knowledge retrieval components in agent applications.

MemVid 是面向 AI Agent 的长期记忆层，利用视频编码实现轻量级单文件存储，替代复杂的 RAG 管线，提供即时检索能力。

图原生的上下文开发平台，提供知识图谱构建、语义检索和可移植的上下文核心，支持 RDF、SPARQL 等标准协议，为 AI Agent 提供结构化知识的存储、丰富和检索能力。