跳到正文
TakoAPI
返回技能列表

lily-memory-5-0-0

由 ksemaj 提供

Coding Agents & IDEs
—暂无评分
你的评分

简介

Persistent memory plugin for OpenClaw agents.

描述

该技能的功能

Persistent memory plugin for OpenClaw agents that survives session resets and restarts. Uses hybrid SQLite FTS5 keyword search combined with Ollama vector embeddings for semantic recall. Automatically extracts and injects relevant facts around each LLM turn.

Combines keyword and semantic search in a single plugin with zero npm dependencies, so agents get accurate retrieval without a separate vector database or additional packages.

何时使用

  • Remembering user preferences across separate agent sessions
  • Tracking project decisions without re-explaining context each time
  • Detecting when an agent is stuck repeating the same topic
  • Looking up all stored facts about a specific entity on demand
  • Running long-term agents that accumulate knowledge over days or weeks

示例工作流

输入

User asks: 'What database did we decide to use for the auth service?'

智能体
  1. 1

    Extract keywords from the user message

  2. 2

    Run FTS5 keyword search against SQLite memory store

  3. 3

    Run Ollama vector similarity search if enabled

  4. 4

    Merge and deduplicate results from both searches

  5. 5

    Inject matching memories as context before sending to LLM

输出

Agent responds with the previously stored decision: 'You decided on PostgreSQL for the auth service on 2025-11-03, preferring it over MySQL for its JSON support.'

前置要求

  • Ollama with nomic-embed-text model (optional, for semantic search)

安装

clawhub install ksemaj/lily-memory-5-0-0

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