Agent Skills › MINT-SJTU/RoboClaw › memory

memory

GitHub

提供双层记忆系统，通过持久化用户偏好、项目上下文及关系事实，并维护追加式事件日志，支持基于文件大小的差异化搜索策略，以增强Agent对历史信息的检索与长期上下文保持能力。

roboclaw/skills/memory/SKILL.md MINT-SJTU/RoboClaw

Trigger Scenarios

需要回忆用户偏好或项目背景查询历史交互记录

Install

npx skills add MINT-SJTU/RoboClaw --skill memory -g -y

More Options

Non-standard path

npx skills add https://github.com/MINT-SJTU/RoboClaw/tree/main/roboclaw/skills/memory -g -y

Use without installing

npx skills use MINT-SJTU/RoboClaw@memory

指定 Agent (Claude Code)

npx skills add MINT-SJTU/RoboClaw --skill memory -a claude-code -g -y

安装 repo 全部 skill

npx skills add MINT-SJTU/RoboClaw --all -g -y

预览 repo 内 skill

npx skills add MINT-SJTU/RoboClaw --list

SKILL.md

Frontmatter

{
    "name": "memory",
    "always": true,
    "description": "Two-layer memory system with grep-based recall."
}

Memory

Structure

memory/MEMORY.md — Long-term facts (preferences, project context, relationships). Always loaded into your context.
memory/HISTORY.md — Append-only event log. NOT loaded into context. Search it with grep-style tools or in-memory filters. Each entry starts with [YYYY-MM-DD HH:MM].

Search Past Events

Choose the search method based on file size:

Small memory/HISTORY.md: use read_file, then search in-memory
Large or long-lived memory/HISTORY.md: use the exec tool for targeted search

Examples:

Linux/macOS: grep -i "keyword" memory/HISTORY.md
Windows: findstr /i "keyword" memory\HISTORY.md
Cross-platform Python: python -c "from pathlib import Path; text = Path('memory/HISTORY.md').read_text(encoding='utf-8'); print('\n'.join([l for l in text.splitlines() if 'keyword' in l.lower()][-20:]))"

Prefer targeted command-line search for large history files.

When to Update MEMORY.md

Write important facts immediately using edit_file or write_file:

User preferences ("I prefer dark mode")
Project context ("The API uses OAuth2")
Relationships ("Alice is the project lead")

Auto-consolidation

Old conversations are automatically summarized and appended to HISTORY.md when the session grows large. Long-term facts are extracted to MEMORY.md. You don't need to manage this.