DeepSeek Harness 插件

dsh-plugin-memtrace

Local-first code intelligence graph for DeepSeek Harness: structural search, blast radius, temporal memory, and 27 agent skills over Memtrace MCP.(英文原文)

跳到安装方式

来源信息

GitHub 仓库
syncable-dev/dsh-plugin-memtrace
最近更新
2026年8月17日
分类
自动化与任务
GitHub stars
0
载体类型
plugin
目录证据
上游声明已找到 dsh.bundle
证据路径
package.json#dsh.bundle
核对版本
0.1.0-rc.8
上游核对日期
2026-08-20

该证据由上游目录提供。本站没有安装、运行或安全审核这个插件。

安装

默认先复制一段 Prompt,让 Agent 读 GitHub 仓库和源码;需要自己装时再切到命令。

复制这段 Prompt,发给 DSH、Codex 或其他 Agent,让它先读 GitHub 仓库和源码。

请先不要安装或执行任何命令。阅读这个插件的 GitHub 仓库、README 和关键源码,然后用清楚、直接的方式回答以下问题,帮助我判断它是否适合我的需求:

1. 这个插件是什么,解决什么问题;
2. 适合哪些用户和典型使用场景;
3. 安装后如何使用,并给出一个最小使用示例;
4. 有哪些已知限制,以及隐私、安全、兼容性或维护风险;
5. 给出“推荐 / 有条件推荐 / 不推荐”的明确建议和理由。

请区分仓库明确说明、根据源码推断和未知信息。证据不足时请明确说明,不要猜测或照抄 README。

GitHub:https://github.com/syncable-dev/dsh-plugin-memtrace
插件名:dsh-plugin-memtrace
作者:syncable-dev

检查来源文件

安装前先看这个插件目录里的 README 和其他文件。

文件资源管理器3 个文件
README.md来源说明 · 只读预览

<p align="center"> <img src="assets/icon.svg" width="96" height="96" alt="Memtrace" /> </p>

<h1 align="center">Memtrace for DeepSeek Harness</h1>

<p align="center"> <strong>The code intelligence graph, as a DeepSeek Harness plugin.</strong><br /> Structural search · blast radius · temporal memory · 27 agent skills </p>

<p align="center"> <a href="https://github.com/deepseek-ai/deepseek-harness"><img src="https://img.shields.io/badge/DeepSeek-Harness-4D6BFE?style=for-the-badge" alt="DeepSeek Harness" /></a> <a href="https://github.com/topics/dsh-plugin"><img src="https://img.shields.io/badge/topic-dsh--plugin-8257D0?style=for-the-badge" alt="dsh-plugin topic" /></a> <a href="https://memtrace.io"><img src="https://img.shields.io/badge/memtrace.io-00D4B8?style=for-the-badge&labelColor=0A1628" alt="memtrace.io" /></a> </p>

<p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="MIT" /></a> <a href="https://github.com/deepseek-ai/deepseek-harness"><img src="https://img.shields.io/badge/DeepSeek%20Harness-plugin-success" alt="DeepSeek Harness plugin" /></a> <a href="https://www.npmjs.com/package/dsh-plugin-memtrace"><img src="https://img.shields.io/npm/v/dsh-plugin-memtrace" alt="npm" /></a> <img src="https://img.shields.io/badge/node-%5E22.19%20%7C%7C%20%3E%3D24-brightgreen.svg" alt="Node" /> <a href="https://github.com/syncable-dev/dsh-plugin-memtrace/actions"><img src="https://img.shields.io/github/actions/workflow/status/syncable-dev/dsh-plugin-memtrace/verify.yml?branch=main&label=CI" alt="CI" /></a> </p>

<p align="center"> <a href="README.md">English</a> · <a href="README.zh.md">简体中文</a> </p>

<p align="center"> <img src="assets/hero.png" alt="Memtrace graph inside DeepSeek Harness" width="100%" /> </p>

---

What you get

One dsh plugin add wires Memtrace into DeepSeek Harness:

SurfaceWhat the agent sees
MCP toolsmcp__memtrace__find_symbol, mcp__memtrace__find_code, mcp__memtrace__get_impact, mcp__memtrace__get_evolution, mcp__memtrace__get_symbol_context, … — the full Memtrace graph, namespaced by the official DSH MCP client
Skills27 Agent Skills (memtrace-first, memtrace-search, memtrace-impact, memtrace-codebase-exploration, fleet coordination, …) registered on ctx.skills
Local-firstThe graph lives on your machine. No cloud index. No repo upload.

Ask the agent: "Index this repo, then show me the blast radius of apply."

It should call Memtrace — not grep.

Quick start

dsh is the DeepSeek Harness CLI (@deepseek-ai/dsh). Install that first — this plugin does not ship it.

# once
npm install -g @deepseek-ai/dsh

# then add Memtrace
dsh plugin --profile web add github:syncable-dev/dsh-plugin-memtrace

# no global install? same command via npx:
npx -y @deepseek-ai/dsh plugin --profile web add github:syncable-dev/dsh-plugin-memtrace

# 2. Restart the profile and confirm the layer
dsh --profile web --dump-config | grep -A4 'id: dsh-plugin-memtrace'

First launch may take a minute while npx memtrace mcp fetches the Memtrace binary. Pin a local install to skip that:

npm install -g memtrace
export MEMTRACE_BIN=memtrace

Then open the Web UI and index the workspace:

> Use Memtrace to index this directory, then give me an architecture briefing.

Install & uninstall

ChannelCommand
Git (main)dsh plugin --profile web add github:syncable-dev/dsh-plugin-memtrace#main
npmdsh plugin --profile web add dsh-plugin-memtrace
Local checkoutdsh plugin --profile web add ./dsh-plugin-memtrace
Uninstalldsh plugin --profile web remove dsh-plugin-memtrace

This package is plain ESM — no prepare script, no allowBuilds prompt.

How it works

flowchart LR
  DSH[DeepSeek Harness] --> Bundle[dsh-plugin-memtrace]
  Bundle --> Skills[ctx.skills.register]
  Bundle --> MCP["@deepseek-ai/dsh-mcp-client"]
  MCP --> Server["memtrace mcp"]
  Server --> Graph[(local code graph)]

Two Cordis rows, both owned by this bundle:

1. dsh-plugin-memtrace — reads skills/*/SKILL.md and registers each skill at apply time. Unload disposes them. 2. mcp-memtrace — official MCP client, serverName: memtrace, stdio. MEMTRACE_BIN overrides the command; otherwise npx -y memtrace mcp.

We do not patch the filesystem skill provider's config. That row is last-write-wins; runtime registration does not collide with other skill packs.

Tools the model gets

After MCP discovery, every Memtrace tool is a native DSH tool under mcp__memtrace__*. The ones agents use first:

ToolUse when
list_indexed_repositoriesCheck what is already in the graph
index_directoryFirst contact with a repo
find_symbol / find_codeLocate a function, type, or behavior
get_symbol_contextCallers, callees, community
get_impactBlast radius before an edit
get_evolutionWhat changed, and when
recall_decisionWhy odd-looking code is there

Full parameter spec: [references/mcp-parameters.md](references/mcp-parameters.md).

Skills

SkillTriggers on
memtrace-firstAny code discovery / "how does this work"
memtrace-index"index this project"
memtrace-search"find this function"
memtrace-impact"what breaks if I change this"
memtrace-evolution"what changed last week"
memtrace-codebase-exploration"I'm new here"
memtrace-code-reviewPR review
memtrace-incident-investigation"something broke"
memtrace-fleet-*Multi-agent coordination

All 27 bundles live under [skills/](skills/).

Configuration

VariableEffect
MEMTRACE_BINAbsolute path or command used instead of npx -y memtrace mcp

Override the MCP row in the profile's cordis.patch.yml if you already run a Streamable HTTP Memtrace endpoint — restate the whole mcp-memtrace config (DSH does not deep-merge).

Compatibility

| Surface | Status | | --- | --- | | Harness | DeepSeek Harness 0.1.0-rc.6+ | | Node | ^22.19.0 \|\| >=24.0.0 | | Platforms | macOS, Linux, Windows (Memtrace native binary via npm optional deps) | | Network | None required after the Memtrace binary is present |

Permissions & data

  • Spawns memtrace mcp in the session working directory (reads the repo to index; writes .memdb next to the project).
  • Registers skills from this package only.
  • Does not send code to Memtrace cloud. Local graph.

Topics

dsh · dsh-plugin · deepseek-harness · cordis · memtrace · mcp

License

[MIT](LICENSE) © 2026 Memtrace / Syncable

Community-maintained Harness plugin. Not an official DeepSeek product.