MemMachine/MemMachine

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

What it solves

MemMachine provides a persistent long-term memory layer for AI agents, preventing them from being stateless. It allows agents to remember user preferences, past conversations, and specific facts across different sessions, restarts, and even when the underlying LLM is changed.

How it works

MemMachine acts as an external memory system that agents interact with via a RESTful API, Python/TypeScript SDKs, or a Model Context Protocol (MCP) server. It categorizes memory into three types:

  • Working Memory: Short-term context for the current session.
  • Episodic Memory: Long-term conversational context stored in a graph database (Neo4j).
  • Profile Memory: Long-term user facts and preferences stored in SQL.

Who it’s for

  • Developers building AI agents, autonomous workflows, or personalized assistants.
  • Researchers exploring cognitive models and agent architectures.
  • Teams requiring cross-session persistence for LLM applications.

Highlights

  • Multi-tier Memory: Separate systems for short-term, episodic (graph-based), and profile (SQL-based) memory.
  • Broad Integration: Compatible with LangChain, LangGraph, CrewAI, LlamaIndex, and n8n.
  • LLM Agnostic: Works with any provider, including OpenAI, Anthropic, Bedrock, and Ollama.
  • MCP Support: Native support for Model Context Protocol to integrate with tools like Claude Desktop and Cursor.

Related

  • Project
    supermemoryai/supermemory

    Supermemory is a hosted‑plus‑self‑hostable memory and context engine for LLM‑based assistants. It extracts facts from chats, emails, PDFs, images, code, etc., builds per‑user profiles (static facts + dynamic recent context), and provides hybrid RAG + memory search through a single API (`add`, `profile`, `search`). Plugins let popular tools (Claude Code, Cursor, Codex) gain persistent memory, while a one‑binary `supermemory local` server lets you run the whole stack offline with local embeddings. The project claims state‑of‑the‑art performance on LongMemEval, LoCoMo and ConvoMem benchmarks (95 % Recall@15 with >99 % context reduction).

  • Project
    mnemon-dev/mnemon

    A persistent, LLM-supervised memory layer for AI agents that enables cross-session knowledge retention across multiple AI frameworks using a four-graph knowledge store.

  • Project
    agentic-box/memora

    An MCP memory layer for AI agents that provides persistent, structured storage and semantic retrieval of facts, tasks, and documents via a knowledge graph.

  • Project
    TencentCloud/TencentDB-Agent-Memory

    A centralized memory server and management hub that allows AI agents to share and reuse distilled experience, skills, and project knowledge across sessions and frameworks.

  • Project
    MemTensor/MemOS

    MemOS 2.0 is a Memory Operating System for LLM‑based AI agents. It offers a unified API to store, retrieve, edit, and delete multi‑modal memories (text, images, tool traces) organized as a graph. The system can run as a hosted cloud service (API‑key access) or be self‑hosted via Docker (Neo4j + Qdrant) or a local SQLite plugin. Ready‑made plugins integrate MemOS with OpenClaw, Hermes, and DeepSeek Harness. Benchmarks show it outperforms existing commercial memory products. Licensed under Apache 2.0.