跳到正文
TakoAPI
返回技能列表

engram-memory

由 dannydvm 提供

Search & Research
1.5k下载量由 clawskills.sh 提供
1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

Persistent semantic memory for AI agents — local, fast, free.

描述

该技能的功能

Local semantic memory system for AI agents. Stores facts, decisions, preferences, and events with biological-style decay, so frequently accessed memories stay relevant. Supports relationship graphs and cross-session context without any cloud dependency.

Runs entirely locally with no API keys or cloud accounts, so memory persists instantly and privately without external service dependencies.

何时使用

  • Recalling a client's preferred tech stack mid-session
  • Storing a decision to pause a campaign for later retrieval
  • Searching past conversation history by topic or type
  • Linking two memories with a 'contradicts' or 'supersedes' relationship
  • Exporting and restoring agent memory across machines

示例工作流

输入

User asks: remember that we decided to use Postgres instead of MySQL for this project

智能体
  1. 1

    Search existing memories for any prior database decisions

  2. 2

    Store new decision memory: 'We decided to use Postgres over MySQL'

  3. 3

    Tag memory with relevant labels (e.g., database, architecture)

  4. 4

    Run auto-relate to link it to any related tech stack facts

  5. 5

    Confirm storage with engram stats

输出

Decision stored, salience-boosted, and linked to related project facts for future recall

安装

clawhub install dannydvm/engram-memory

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