跳到正文
TakoAPI
返回技能列表

persisent-mind

由 vedantsingh60 提供

Search & Research
350下载量由 clawskills.sh 提供
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, searchable, context-aware memory for AI agents.

描述

该技能的功能

PersistentMind is a Python library that stores typed, searchable memories for AI agents across sessions. It supports seven memory types (fact, preference, procedure, correction, context, relationship, reminder) and three scopes (global, project, session). Data is stored locally with no external dependencies or API keys.

Unlike static prompt files or manual re-explanation, it ranks memories by importance and type, surfacing critical corrections first in every injected context block.

何时使用

  • Persisting code style corrections so agents stop repeating the same mistakes
  • Storing project-specific commands like migration or deployment steps
  • Injecting accumulated project context into new chat sessions automatically
  • Building a shared team knowledge base via JSON export and import
  • Setting temporary notes that auto-expire after a specified number of days

示例工作流

输入

User asks: Remember that we never use wildcard imports and that migrations run with 'poetry run alembic upgrade head'

智能体
  1. 1

    Call remember() with the wildcard import rule as MemoryType.CORRECTION, scope PROJECT, importance 10.0

  2. 2

    Call remember() with the migration command as MemoryType.PROCEDURE, scope PROJECT

  3. 3

    In the next session, call get_context(project='my-app') to retrieve stored memories

  4. 4

    Prepend the formatted context block to the incoming user prompt

输出

Context block with the correction surfaced first, followed by the procedure, automatically prepended to every subsequent prompt

安装

clawhub install vedantsingh60/persisent-mind

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