mem0 and dna-memory
About mem0
mem0ai/mem0
Universal memory layer for AI Agents
Implements multi-level memory (user, session, agent state) with adaptive retrieval that achieves 26% higher accuracy and 90% lower token usage than baseline approaches. Supports multiple LLMs and vector stores, with SDKs for Python and JavaScript, plus integrations for LangGraph and CrewAI. Offers both self-hosted open-source deployment and a managed platform with CLI tooling for memory management operations.
About dna-memory
AIPMAndy/dna-memory
🧬 让 AI Agent 像人脑一样学习成长 | Memory that learns, forgets, and evolves
Implements a three-tier memory hierarchy (working/short-term/long-term) with active forgetting via weight decay, automatic pattern reflection, and SQLite FTS5 full-text search—all running locally with zero external dependencies. The architecture includes a background daemon for autonomous memory consolidation and promotion, designed specifically for agent feedback loops where experiences get reinforced, forgotten, or elevated to stable long-term knowledge.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work