@deepseek-ai/dsh-plugin-memory
适用于 DeepSeek Harness 的持久化五层记忆系统（条目注入、相关性检索、智能体工具和基于 LLM 的自动提取）。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:NattoCB/dsh-plugin-memory#468f2a8f36f256fe90d6a97d43e68b639c21436aPlugin Memory 以 @deepseek-ai/dsh-plugin-memory 发布，当前版本为 0.1.0-rc.1。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | 中文
agent/pre-step injection + ctx.tools.register (six tools)
A persistent five-layer memory system for DeepSeek Harness (DSH): a user profile (L1), a per-project semantic index with topic files (L2), and append-only per-day logs (L3) under
~/.dsh/memory/and<cwd>/.dsh/memory/. It injects relevant memories into every request and auto-extracts durable facts from finished sessions via the LLM. Integrates as a DSH plugin on two cordis seams —agent/pre-stepfor injection,ctx.tools.registerfor sixmemory_*agent tools. Without anllmroute it still works: entry injection, keyword relevance, and profile rotation remain; only LLM ranking and auto-extraction are disabled.
~/.dsh/AGENTS.md, not managed by the plugin) → L1 profile → L2 project index + topics → L3 per-day append-only log → L4 skills (existing). Each layer has its own write path, truncation budget, and injection rule.MEMORY.md is always an index of one-line pointers (≤150 chars each); details live in <topic>.md. Keeps single files small, searchable, and truncatable.llm is configured, keyword scoring otherwise) and appends them as a <system-reminder data-role="memory"> block; files already surfaced in this session are de-duplicated. The two channels are labeled memory-entry (once per session) and memory-relevance (per step) in the GUI context rows.memory_profile merges new facts into four fixed sections (工作背景 / 个人背景 / 当前关注 / 近期动态) and rotates the version, keeping the previous copy in profile.md.bak.fs/promises directly to the memory roots — intended persistence, not self-modification — and paths are confined to the store root. Memory files are context the agent reads back, never permission grants.<uid> layer.ctx.tools.register (defineTool from @deepseek-ai/dsh-tools):| Tool | Scope | Effect |
|---|---|---|
memory_write | global/project | Write/overwrite a topic file; optionally add an index line. |
memory_read | global/project | Read a topic file or the MEMORY index. |
memory_search | global/project/both | Keyword-search topic files. |
memory_daily | cwd | Append a dated line to <cwd>/.dsh/memory/YYYY-MM-DD.md. |
memory_forget | global/project | Delete a topic file and its index pointer. |
memory_profile | global | Read, or merge-and-rotate, the single-user profile. |
web).dsh plugin --profile web add github:NattoCB/dsh-plugin-memory
Restart dsh web. On first use the plugin bootstraps both memory roots:
~/.dsh/memory/
MEMORY.md # global index (≤200 lines / 40K chars)
profile.md # L1 profile (Version N)
profile.md.bak # previous profile version
<topic>.md # global topic files
<cwd>/.dsh/memory/
MEMORY.md # project index
YYYY-MM-DD.md # daily memory (append-only)
<topic>.md # project topic files
Tell the agent something worth remembering, or let idle auto-extraction pick it up — then check the memory roots a session later.
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
MIT — see LICENSE.