CaviraOSS/OpenMemory
A self-hosted, local-first cognitive memory engine providing real long-term memory for LLM applications and AI agents, distinct from RAG or vector databases.
Core Features
Quick Start
docker compose up --build -dDetailed Introduction
OpenMemory is a unique cognitive memory engine designed to give LLMs and AI agents true long-term memory, addressing the inherent statelessness of models. Unlike traditional RAG or vector databases, it aims for a more profound memory mechanism. It's self-hosted and local-first, offering flexibility with SQLite or Postgres. Developers can integrate it via Python and Node.js SDKs, or deploy it as a central backend server with an HTTP API and dashboard. It also features connectors to ingest data from various external sources, making it a comprehensive solution for building 'non-amnesiac' AI applications.