lxfight-s-Astrbot-Plugins/astrbot_plugin_livingmemory

一个拥有动态生命周期的智能长期记忆插件。

What it solves

It provides a long-term memory system for AstrBot, allowing AI agents to remember user preferences, character relationships, project progress, and historical agreements across different conversations instead of relying solely on short-term context windows.

How it works

LivingMemory automatically organizes dialogue history into long-term memories after a set number of conversation turns. It uses a combination of keyword search, vector retrieval (semantic search), and knowledge graphs to recall relevant information. The system manages the memory lifecycle through archiving, decay, and access reinforcement. Additionally, agents can actively read and write memories using specific tool calls (recall_long_term_memory and memorize_long_term_memory).

Who it’s for

Users of AstrBot who want their AI assistants to have a persistent, evolving memory of their interactions and a way to visually manage those memories.

Highlights

  • Hybrid Recall: Combines keyword and vector retrieval with graph-based navigation for high-accuracy memory retrieval.
  • Agentic Memory: Allows the AI agent to proactively trigger memory recall and storage.
  • Visual Management: Includes a dedicated web interface (Pages) to browse relationship graphs, edit memories, and test recall functions.
  • Customizable UI: Offers four distinct visual themes (Editorial, Studio, Paper, and Terminal) for the management dashboard.

Related

  • Project
    menglimi/astrbot_plugin_private_companion

    A full‑featured AstrBot plugin that adds continuous life‑state, schedule, relationship and proactive‑message handling to make the bot act like a virtual companion.

  • Project
    supermemoryai/openclaw-supermemory

    A plugin for OpenClaw that adds long-term memory by automatically capturing, storing, and recalling conversation context via the Supermemory cloud service.

  • 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
    MemTensor/MemOS-Cloud-OpenClaw-Plugin

    A lifecycle plugin for OpenClaw and related hosts that integrates MemOS Cloud to provide AI agents with persistent memory recall and message storage.

  • Project
    EverMind-AI/EverOS

    EverOS is a Python library that provides local‑first, Markdown‑backed memory for AI agents. It syncs files to SQLite and LanceDB, offers a simple HTTP API for add/flush/search, and works with a single OpenRouter key for keyword search. Optional extras add embedding‑based hybrid search, reranking, and multimodal file ingestion.