# ReMe — DeepSeek Harness plugin install manifest

> Generated: 2026-09-13 19:09 · Source: https://deepseekmodel.com/plugins

## Overview

Turns conversations and resources into readable, editable, searchable and interlinked Markdown memory, with a shared workspace across agents.

## What it does

- Memory is stored as Markdown files, with persistent files always under user control
- Agents like QwenPaw and DSH can share one workspace to retrieve and maintain it
- Knowledge keeps being retrieved, maintained and evolved instead of one-off context

## Plugin info

| Category | Maintainer | GitHub stars | License | Primary language | Last push |
| --- | --- | --- | --- | --- | --- |
| Memory | agentscope-ai | 3,441 | Apache-2.0 | Python | 2026-09-09 |

## Install

```bash
dsh plugin add github:agentscope-ai/ReMe
```

## Steps

1. Install and start DeepSeek Harness (DSH, MIT-licensed open-source agent runtime) — `npx @deepseek-ai/dsh web`
2. Run the command above; the CLI resolves the plugin and verifies its source
3. Confirm with dsh plugins list; restart Harness if needed

> To pin a revision, append #commit to the repository spec.

## Audit before installing

Plugins run with your dsh process permissions and may execute code during installation. Read the repository source and license first, check for destructive commands or excessive access, and pin a commit hash for reproducible installs. This manifest is compiled by DeepseekModel from a public plugin catalog for reference only and does not vouch for third-party plugins.

---

- Repository: https://github.com/agentscope-ai/ReMe
- Plugin page: https://deepseekmodel.com/plugin-detail?id=reme
- Source: https://deepseek-harness-plugin.com/zh-CN/plugins/ · Generated 2026-09-13