Memory System Python Packages

hermes-next

Next-generation memory provider for Hermes Agent — fusing OpenViking vector storage with MemOS cognitive engine

memorius

Memorius is a self-contained, agent-agnostic memory system that gives LLMs and AI agents persistent, searchable memory with a hierarchical knowledge organization. Drop-in with multi-backend vector storage, pluggable embeddings, built-in MCP + REST servers, and auto-detecting agent hooks for 7 different AI coding agents.

adclaw

Open-source multi-agent AI marketing team with personas, shared memory, 130+ skills, and Docker deploys for Railway and DigitalOcean

mark-sdk

Local-first cognitive memory runtime for agent applications.

body-emotion-sensor

Body emotion mapper: structured emotion analysis (AnalysisInput) JSON to body-axis states and prompt tags

langchain-superlocalmemory

SuperLocalMemory V3 integration for LangChain — local-first AI memory with mathematical foundations

rag-mem

Production-ready AI infrastructure: RAG with smart reindexing, persistent memory, browser automation, and MCP integration. Stop rebuilding tools for every AI project.

nexus-agent-memory

Cross-session persistent memory for AI Agents. 4500x faster retrieval, zero LLM dependency.

mnemoria

Cognitive memory for AI agents — ACT-R activation, typed facts, Hebbian links, RL reranking, continuous extraction

snipara-memory

Standalone memory engine for coding agents

relational-memory

A relationship-aware memory layer for LLM chatbots — models the relationship, not just facts