dsh-project-memory

DeepSeek Harness Memory Low risk

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

北极星记忆：DeepSeek Harness 本地优先项目记忆插件。每项目一份 .dsh-memory.json（按 cwd 隔离），提供 memory_read/recall/write/update/delete 工具、/memory 命令与设置页；分级注入（用户画像常驻 + 场景触发记忆带 P1/P2/P3 等级）、语义召回（IDF+同义词层）、底线记忆硬守卫机制（识别禁止语义→授权→拦截 AI 删除；用户可确认绕过）。

How to install

DeepSeek Harness dsh plugin add github:LAYZR114/dsh-project-memory

About

🌟 北极星记忆（dsh-project-memory）· Project Memory Plugin for DeepSeek Harness **版本**：0.1.3 · **许可证**：BSD-3-Clause · **类型**：DeepSeek Harness（DSH）插件 · **适配核心**：DSH **v0.1.5-rc.1 及更新**（web/desktop profile 通用；桌面端 2.0.7+，实测 2.0.9 / 核心 0.1.5-rc.1） **版本线**：🚀 **单线（0.1.3）** —— 2026-09-11 起取消双线，**只跟随 DSH 最新核心，不再为旧核做适配**；旧的自用稳定线 0.1.4 已归档（D:\Agent共享\DSH插件\归档-legacy线-20260911\）。**只有出现较大优化或新功能时才升 0.2.0**；**本版暂不发布**（0.1.4/0.1.5 这两个双线版本号作废）。详见 VERSION-LINES.md **0.1.3 界面修复·第三轮（2026-09-12 用户实测驱动）**：① 修复「点目录输入框却输入到搜索框」——根因是搜索框的 autoFocus 与**回调 ref 里的 focus()**（React 每次渲染都重新调用回调 ref → 每次抢焦点）；最终改为**结构性根治：搜索框收起时从 DOM…

GitHub ↗

Recommendation signals

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

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

45 Overall

0views

0unique visitors

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ Report issue ↗

Basic safety check

Findings: curated 收录但无 npm 包/安装命令
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics: dsh-plugin, skills

Related plugins

Claude Code

Score82

get-shit-done

gsd-build/get-shit-done

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

☆ 64.5K ↓ 48.4K Memory ↗

MCP ServerClaude Code

Score80

markdownify-mcp

zcaceres/markdownify-mcp

A Model Context Protocol server for converting almost anything to Markdown

☆ 3.0K ↓ 1.3K Memory ↗

DeepSeek Harness

Score80

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.

☆ 23.6K ↓ 119.1K Memory ↗

MCP Server

Score79

airtable-mcp-server

domdomegg/airtable-mcp-server

🗂️🤖 Airtable Model Context Protocol Server, for allowing AI systems to interact with your Airtable bases

☆ 456 ↓ 13.1K Memory ↗