dshbase

插件目录 / Knowledge / dsh-claude-mem

dsh-claude-mem

已验证 · 实测可装 Bleed00

✓ 持续维护 基于 6 个官方 DSH 包 纯 TypeScript

查看 GitHub ↗ ← 返回插件目录

1Stars
0Forks
0未关闭 issue
TypeScript语言
2026-08-15最近推送
跨平台平台

功能简介

dsh-claude-mem — DSH 插件(会话)

✅
我们的评价
可用 — 实测通过,早期项目

dsh-claude-mem — DSH 插件(会话) 实测能干净安装、正常启动。早期项目,但功能可用。

「已验证」表示我们的自动化 CI 在干净 profile 里实际执行了 dsh plugin add 并启动成功——仅此而已。功能描述与版本兼容性均为作者声明。这不是安全审计,也不代表对第三方代码的背书。

README

dsh-claude-mem

A DeepSeek Harness plugin that integrates claude-mem: query persisted cross-session memory, inject per-project context at session start, save manual memories, and drive session summarization — all through a local claude-mem worker's HTTP API.

npm
npm downloads
GitHub
CI
License
TypeScript
Node.js
DeepSeek Harness
dsh-plugin

It registers the model-facing tools mem_search, mem_timeline, mem_get_observations, mem_save, and mem_context, the mem-search skill, and the lifecycle hooks (agent/session-start context injection, optional tools/post-execute ingestion, optional agent/turn-stopping summarization). It is a single self-contained package with no monorepo-only dependencies.

Install

One-liner with npx (no global install — npx fetches the dsh launcher and
dsh plugin forwards add to pnpm in the target profile):

npx -y @deepseek-ai/dsh plugin --profile demo add @bleed00/dsh-claude-mem

If you already have dsh on PATH, the same command without npx:

dsh plugin --profile demo add @bleed00/dsh-claude-mem

npm (recommended — ships prebuilt lib/, no build permission needed):

npx -y @deepseek-ai/dsh plugin --profile demo add @bleed00/dsh-claude-mem

GitHub (sources; runs a prepare build on first install):

npx -y @deepseek-ai/dsh plugin --profile demo add github:Bleed00/dsh-claude-mem

A GitHub install fetches sources, not build output, so pnpm runs this package's prepare script to build from src/. pnpm ≥10 refuses to run a git dependency's prepare until it is allowlisted; the first add fails and points at the fix — copy the exact package key pnpm printed into the profile's pnpm-workspace.yaml:

allowBuilds:
  '@bleed00/dsh-claude-mem': true

then re-run the add. Treat that allowance as permission to run this package's code at install time; pin a commit for reproducible installs:

dsh plugin --profile demo add github:Bleed00/dsh-claude-mem#<sha>

Local checkout:

dsh plugin --profile demo add ./dsh-claude-mem

Requirements

  • A DeepSeek Harness installation with dsh on PATH.
  • The claude-mem worker already running on its default port (http://127.0.0.1:37700). Override with the baseUrl config or the DSH_MEM_BASE_URL environment variable.

Config

Field Default Description
baseUrl http://127.0.0.1:<37700 + uid % 100> Worker base URL.
timeoutMs 30000 Per-request timeout (ms).
dedupe true Collapse duplicate observations in query results (content fingerprint, never identity).
platformSource unset Optional platform filter; omitted = search all memory.
project unset Project name; defaults to the session cwd basename.
injectContext true Inject session-start context.
ingest false Save observed tool results as memories.
summarize false Summarize sessions on turn stop.
toolFilter.names read, write, edit, bash Tools observed when ingest is true.

Platform scoping is a signal, never a restriction: default requests are unfiltered, and platformSource only adds an opt-in filter.

Duplicate handling

The worker can persist the same observation many times (a boilerplate "session
initiated" record, or a re-run tool result) — identical content, different id.
With dedupe: true (the default), query results collapse those copies: an
observation's content fingerprint is built from title + subtitle +
text + narrative + facts (normalized), so two entries that merely share a
generated title but differ in narrative are kept. The first copy (lowest id)
is retained. Structured results (mem_get_observations) are deduplicated by
fingerprint; rendered index/text results are deduplicated by exact rendered
row. Set dedupe: false to see the raw, unfiltered results.

Example override in the profile's cordis.patch.yml

- id: claude-mem
  config:
    baseUrl: http://127.0.0.1:37700
    platformSource: dsh
    ingest: true
    summarize: true

Tools

Tool Purpose
mem_search Search memory; returns an index (ids, titles, types).
mem_timeline Get context around one observation.
mem_get_observations Fetch full details for ids.
mem_save Save one manual memory.
mem_context Render the worker's session-start context text.

The mem-search skill teaches the model the search → filter → fetch workflow that keeps token usage low.

Development

pnpm install
pnpm run build   # tsc + tsdown → lib/index.js
pnpm test

The package targets Node ≥ 20.12, TypeScript 6.0, and is authored against the @deepseek-ai/* framework packages (cordis, schemastery, dsh-tools, dsh-llm, dsh-skill, dsh-agent).

License

Apache-2.0 © Bleed00

安装

🧩 让 Agent 自动装(推荐)

装一次目录插件,之后本站所有插件都能让 DeepSeek Harness 自动找、自动装:

dsh plugin add dshbase-catalog

然后对 agent 说「帮我装 dsh-claude-mem」,它会在目录里找到并自动安装。文档:dshbase-catalog · 已验证场景包。

该插件是 GitHub 源码(未发 npm)——直接从仓库装:

Web profile:

dsh plugin --profile web add github:Bleed00/dsh-claude-mem

Headless(CLI)profile:

dsh plugin --profile headless add github:Bleed00/dsh-claude-mem

实测报告

验证通过:从 GitHub 源码完成 L1 安装 + L2 加载 + L3 运行(dsh 0.1.0-rc.6)。

使用场景

给 agent 一套记忆、知识库或检索层,让它不再跨会话丢上下文。

适合谁

跑长项目、想让 agent 记住决策、文档和偏好而不用每次重讲的人。

二次开发建议

记忆/检索后端是缝——插新存储、调蒸馏策略,或加引用与审计轨迹。

安全:尚未扫描——我们的每日静态扫描将很快覆盖它。

分享徽章

Knowledge 里更多

浏览全部 7797 个插件 →