doublehappy123/dsh-memory0

dsh-memory

DeepSeek Harness 长期记忆插件:回答前自动召回相关记忆,回答后自动保存关键事实,提供增删改查工具及可视化管理页。

AI 分析

核心用途是为模型赋予跨会话的长期记忆能力。适合需要模型记住用户偏好、历史设定或关键事实的个性化助手任务。提供 5 个自动调用的记忆管理工具。

包名
dsh-memory
版本
1.1.0
许可证
MIT
最近更新
2026年9月2日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:doublehappy123/dsh-memory

Usage

Model tools

The plugin registers 5 tools that the model can call automatically:

ToolDescription
memory_saveSave a fact/preference to long-term memory
memory_recallSearch memory by keywords/tags, returns ranked results
memory_listList all memories (paginated, tag-filterable)
memory_updateUpdate an existing memory by ID
memory_deleteDelete a memory by ID

The system prompt instructs the model to:

  1. Call memory_recall before answering to retrieve relevant context
  2. Call memory_save after answering when new worth-remembering facts emerge

Visual settings page

After installation, open Settings长期记忆 (Long-term Memory) in the dsh web UI. You can:

  • Browse all memories as cards with tags, importance stars, and timestamps
  • Real-time search by content or tags (300ms debounce)
  • Add new memories with content, tags, category, and importance (1-5 stars)
  • Edit existing memories
  • Delete memories (with confirmation)
  • Paginate through large memory collections (20 per page)
  • Export all memories to a downloadable JSON file
  • Import memories from a JSON file (merge mode: dedupe by ID, update existing, add new)