MemTensor/MemOS-Cloud-OpenClaw-Plugin

Official MemOS Cloud plugin for OpenClaw. Enables long-term memory for agents by recalling context before execution and saving conversations after each run.

What it solves

This plugin enables AI agents hosted on OpenClaw, Moltbot, or ClawDBot to maintain a persistent long-term memory via MemOS Cloud. It solves the problem of agents forgetting user preferences and past interactions by automatically recalling relevant memories before a prompt is processed and saving new interactions after the run ends.

How it works

The plugin integrates into the agent's lifecycle via two primary hooks:

  • Recall: During the before_prompt_build phase, the plugin sends a search request to MemOS Cloud using the user ID and prompt. It can optionally use a secondary LLM to filter the retrieved memories for relevance before injecting them into the system context.
  • Add: During the agent_end phase, the plugin captures the last turn of the conversation (user and assistant messages) and uploads them to MemOS Cloud for future recall.

It supports multi-agent architectures by isolating memory based on agent_id, allowing different agents to have unique knowledge bases and recall settings. It also provides a local web-based configuration UI for managing settings.

Who it’s for

Developers using OpenClaw, Moltbot, or ClawDBot who want to add persistent, cloud-based memory and personalized context to their AI agents.

Highlights

  • Automated Memory Lifecycle: Handles both the retrieval of past context and the storage of new messages automatically.
  • Multi-Agent Isolation: Supports distinct memory stores and configurations for different agents within the same system.
  • Model-Based Filtering: Optional second-pass filtering using an OpenAI-compatible model to ensure only the most relevant memories are injected.
  • Flexible Configuration: Offers a local UI for config editing and supports environment variable overrides across multiple host platforms.

Related

  • Project
    CortexReach/memory-lancedb-pro

    memory‑lancedb‑pro is a production‑grade OpenClaw plugin that gives AI agents persistent, searchable memory. It auto‑captures conversation snippets, classifies them with an LLM, stores them in a LanceDB vector+BM25 index, and automatically injects the most relevant memories into prompts. Features include hybrid retrieval, cross‑encoder reranking, Weibull‑based forgetting, per‑agent/user/project scopes, and support for any OpenAI‑compatible embedding provider. Install via a one‑click script or the OpenClaw CLI, configure with a short JSON block, and manage the store with a built‑in CLI.

  • Project
    supermemoryai/opencode-supermemory

    A plugin for OpenCode that adds persistent, long-term memory to AI agents, allowing them to remember project details and user preferences across sessions.

  • Project
    MemTensor/MemOS

    A memory operating system for LLMs and AI agents that provides persistent, multi-modal long-term memory and unified management tools.

  • Project
    BAI-LAB/MemoryOS

    MemoryOS is a memory management system for AI agents that uses a hierarchical storage architecture to maintain short, mid, and long-term personalized memory for more coherent interactions.