dsh-plugin

DeepSeek Harness Memory Low risk

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

PLUR 记忆在每次组装时渲染进系统提示词，而非以工具调用形式暴露，因此记忆块是被替换而不是追加，整段会话的上下文长度保持不变。全本地混合检索（BM25 + BGE，RRF 融合）、可直接编辑的纯 YAML 存储、按工作区划分 scope，并提供 /plur-memory 浏览器界面。

How to install

DeepSeek Harness dsh plugin add @plur-ai/dsh

About

@plur-ai/dsh **Persistent memory for DeepSeek Harness. Your agent corrected on Monday remembers on Tuesday.** English | 中文 **Source lives in the PLUR monorepo.** This repository is the plugin's public entry point — the npm package is built and published from the monorepo. Open issues and pull requests there. Exposing memory as a tool is the common pattern — the model still has to decide to call it. This one puts the memories themselves in the prompt. Overview DeepSeek Harness starts every session knowing nothing about you. You re-explain the same conventions, corrections and preferences you ex…

GitHub ↗

Recommendation signals

49 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

49 Overall

0views

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ npm ↗ Homepage ↗ Report issue ↗

Basic safety check

Findings: None
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin, curated:0xsline/awesome-deepseek-harness
Topics: agent-memory, cordis, deepseek-harness, dsh-plugin, llm-memory, local-first, persistent-memory, plur

Related plugins

DeepSeek Harness New

Score97

hindsight

vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

☆ 20.0K ↓ 116.9K Memory ↗

MCP ServerClaude Code New

Score93

firecrawl-mcp-server

firecrawl/firecrawl-mcp-server

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

☆ 7.3K ↓ 522.5K Memory ↗

Claude CodeCodex New

Score80

hivemind

activeloopai/hivemind

Hivemind turns your traces into reusable skills across agents

☆ 1.6K ↓ 4.3K Memory ↗