跳到正文
TakoAPI
返回技能列表

simplemem

由 nantes 提供

Search & Research
383下载量由 clawskills.sh 提供
2星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Efficient Lifelong Memory for LLM Agents - semantic compression, cross-session memory, and intent-aware retrieval.

描述

该技能的功能

SimpleMem gives LLM agents persistent memory across sessions by compressing interactions into compact units and retrieving them based on intent. It uses a multi-index approach combining semantic, lexical, and symbolic layers. Without an OpenAI key, it falls back to JSON-based keyword search.

Unlike naive context stuffing, SimpleMem compresses and indexes memories so retrieval stays fast and relevant even as history grows.

何时使用

  • Remembering user preferences across chat sessions
  • Storing project context for long-running agent tasks
  • Reducing repeated context in multi-turn conversations
  • Retrieving relevant past interactions during planning
  • Compressing conversation history to stay within token limits

示例工作流

输入

User asks: Remember that I prefer dark mode and always use TypeScript

智能体
  1. 1

    Calls simplemem add with the preference string and a user ID

  2. 2

    SimpleMem compresses and stores the memory unit in persistent storage

  3. 3

    In a later session, agent calls simplemem retrieve with query about user preferences

  4. 4

    SimpleMem runs intent-aware search across semantic and lexical indexes

  5. 5

    Returns ranked memory results with the stored preference

输出

Agent recalls dark mode and TypeScript preference without re-prompting the user

前置要求

  • OPENAI_API_KEY environment variable (optional, required for semantic embeddings)

安装

clawhub install nantes/simplemem

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接