← Back to list

dsh-meow-memory

DeepSeek Harness Memory Low risk

Project-scoped cross-session memory: seven-layer SQLite store (soul/user/project/fact/lesson/rules/topic) on node:sqlite, cache-friendly first-message injection plus per-message keyword hits, memory_remember/search/find_similar/read/update/project tools, and idle-window consolidation ("dream") with peak-hour suppression. Prompt texts ship as per-language data files — the framework supports multilingual users.

项目级跨会话记忆:node:sqlite 七层存储(soul/user/project/fact/lesson/rules/topic),首条消息缓存友好注入 + 每条消息关键词命中,memory_remember/search/find_similar/read/update/project 工具,空闲窗口自动整理记忆(dream,峰时抑制)。prompt 文案按语言数据文件加载——框架支持多语言用户。

How to install

DeepSeek Harness dsh plugin add meow-memory

About

meow-memory 🐱📝 | 中文 | English | MIT License | | :---: | :---: | :---: | 为 DeepSeek Harness(DSH)打造的跨会话记忆插件。 **核心理念**:每个工作区维护一份结构化记忆数据库(.dsh-meow/memory.db,基于 node:sqlite)。 静态工具手册(七层结构 + 每个 memory_* 工具的用法)以固定 section 的形式放在 **system prompt** 里—— 文本恒定,因此不会破坏 LLM provider 的 KV/上下文缓存。动态内容(soul/user 全量、设计原则、 记忆导引)作为**第一条用户消息的前缀**注入,且首轮只注入长期记忆、不做关键词命中; 从第二轮起每条用户消息做关键词命中(top-2)。模型按需用 memory_search / memory_project 深入检索。每个窗口由自己的主 agent 在夜间("dream")整理记忆, 且只整理自己的记忆——以窗口最后一次对话时间戳冻结其知识。 ✨ 功能特性 **七层记忆**(soul = AI 自身 / user = 用户基本信息与偏好 / project = 项目信息, 含 subcategory(overview/structure/decisions/quotes/ops/…

Recommendation signals

64 Tool quality · Based on stars, downloads, maintenance, security and docs
– User interest · Adjusted by in-site views, install copies and download clicks
64 Overall
0views
0unique visitors
0install copies
0download clicks
0outbound clicks

Meta

License
MIT
Language
TypeScript
GitHub stars
117
mo. downloads
–
Last push
2026-09-23
Created
2026-08-14

Links

Basic safety check

Findings
None
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics
agent-memory, deepseek-harness, dsh, dsh-plugin, memory

Related plugins

DeepSeek Harness
Score98

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.

☆ 27.7K ↓ 124.6K Memory ↗
MCP ServerClaude Code
Score91

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.

☆ 7.5K ↓ 126.7K Memory ↗
DeepSeek Harness
Score84

dsh-mnemon

omdsh-dev/dsh-mnemon

Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.

☆ 409 ↓ 36.1K Memory ↗
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 ↗