DeepSeek HarnessHub
提交插件

wwskills/dsh-long-memory ↗★ 0

@wwskills/dsh-long-memory

DSH 跨会话长期记忆插件，基于 SQLite 支持 FTS5 关键字检索与向量嵌入召回。

AI 分析

核心用途是实现智能体的跨会话长期记忆。适合需要智能体记住历史对话设定、支持本地 Ollama 或 OpenAI 向量检索的复杂任务场景。

memory效率
套件
@wwskills/dsh-long-memory
版本
0.1.0
授權
MIT
最近更新
2026年8月25日

安裝

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

說明文件

閱讀完整 README ↗

Configuration

Defaults are sensible. Override via your profile's patch layer as needed.

Embedding

ProviderUse caseCost
noneFTS5 keyword only (default)Zero
ollamaLocal Ollama serviceZero (local)
openai-compatibleAny OpenAI-style APIPer-call
- id: long-memory
  config:
    embedding:
      provider: 'ollama'          # 'none' | 'ollama' | 'openai-compatible'
      model: 'bge-m3'
      dimension: 1024
      ollama:
        base_url: 'http://127.0.0.1:11434'

L7 Auto-extraction

L7 reads your DSH LLM provider config automatically — no extra API key needed.

- id: long-memory
  config:
    l7:
      enabled: true               # enable auto memory extraction
      auto_extract: true          # LLM-based + keyword fallback
      extractor_model: ''         # empty = use cheapest model from your DSH config
      extractor_temp: 0.2
      interval_ms: 21600000       # 6h minimum between extractions

Storage

    storage:
      path: '${DSH_HOME}/long-memory/long-memory.db'
      markdown_dir: '${DSH_HOME}/long-memory/markdown'