@deepseek-ai/dsh-plugin-memory

Persistent 5-layer memory system for DeepSeek Harness (entry injection, relevance retrieval, agent tools, and LLM-backed auto-extraction). 适合需要AI跨会话长期记住个人偏好和项目背景信息的用户。

パッケージ

@deepseek-ai/dsh-plugin-memory

互換性

未検証

Harness ピア範囲

^0.1.0-rc.6

Cordis ピア範囲

^4.0.1

バージョン

0.1.0-rc.1

ライセンス

MIT

最終更新

2026/08/21

Configuration

Deploy the plugin via a DSH bundle entry (see cordis.patch.yml and package.json exports):

Key	Default	Meaning
`enableEntryInjection`	`true`	Prepend the how-to-save + index block once per session.
`enableRelevance`	`true`	Append relevant topic files per step (`data-role=memory`).
`enableExtraction`	`true`	Idle-time LLM auto-extraction.
`maxRelevant`	`5`	Max files surfaced per step (1–20).
`relevanceTopK`	`8`	Max candidates the LLM selector may pick from (1–40).
`relevanceBudgetChars`	`2000`	Per-topic char cap fed to relevance selection (≥200).
`extractionDebounceMs`	`60000`	Idle debounce before an extraction pass runs.
`extractionLookback`	`40`	Recent events scanned per pass (5–200).
`llm.provider`	`""`	Provider for extraction / relevance ranking (empty → keyword-only).
`llm.model`	`""`	Model for extraction / relevance ranking.
`llm.maxTokens`	`1024`	Completion token cap for LLM calls.

Example entry:

- id: memory
  name: '@deepseek-ai/dsh-plugin-memory'
  config:
    enableEntryInjection: true
    enableRelevance: true
    enableExtraction: true
    maxRelevant: 5
    relevanceTopK: 8
    relevanceBudgetChars: 2000
    extractionDebounceMs: 60000
    extractionLookback: 40
    llm:
      provider: deepseek   # example: fill in your route
      model: deepseek-chat
      maxTokens: 1024

@deepseek-ai/dsh-plugin-memory

インストール

ドキュメント

Configuration