Ori-Mnemos

Ori Mnemos is an open-source persistent memory infrastructure for AI agents that implements human cognition models on a knowledge graph. It uses ACT-R decay, spreading activation, and Hebbian learning to manage memory, and achieves state-of-the-art retrieval performance while being zero-infrastructure and portable.

Ori-Mnemos sits in the Memory & Context category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Persistent memory across sessions, clients, and machines. A representative use case is Multi-hop retrieval QA (e.g., HotpotQA). The listed license is Apache-2.0. GitHub stars are currently 331. Relevant tags include agent-memory, ai-agent.