← Back to list

dsh-prime-memory

DeepSeek Harness Memory New Low risk

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

分层记忆插件,面向 Agent 暴露 10 个工具:高权限写入(memory_add / memory_delete / memory_import)、反刍控制(memory_ruminate / _cancel / _status)与记忆图谱(memory_search_graph / memory_expand_graph_node),底层为 L0–L3 蒸馏管线,并在每步模型调用前召回注入相关记忆。

How to install

DeepSeek Harness dsh plugin add dsh-prime-memory

About

alt="DeepSeek Harness hero 横幅:对话自动分层蒸馏成记忆,模型每步前自动召回注入——右侧对话气泡逐层溶解为三层渐亮光带,流入带发光圆球与渐变轨道的玻璃胶囊(下有 日常·工作·智能·关闭 四档刻度),光丝回流示意召回注入"> dsh-prime-memory **DeepSeek Harness 的分层蒸馏记忆插件:对话在后台自动完成 L0 捕获 → L1 原子记忆 → L2 场景整合 → L3 画像蒸馏,模型每一步前自动把相关记忆注入上下文。** English · 最新发行版 · 反馈问题 中文 README English README 日本語 README 한국어 README 安装指南(中文) Installation guide (English) 日本語インストールガイド 한국어 설치 안내 更新日志(中文) Changelog (English) 日本語 changelog 한국어 changelog DSH 版本兼容矩阵 | DSH 版本 | settings 注册 API | 状态 | |---|---|---| | 0.1.1-rc.2 | settings.register()(live scope) | ✅ 已验证 | | 0.1.2-rc.1 | settings.register()(回退可用) | ⚠️ 按框架文档推断,未实测…

Recommendation signals

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

Meta

License
MIT
Language
TypeScript
GitHub stars
1
mo. downloads
1.8K
Last push
2026-09-20
Created
2026-09-01

Links

Basic safety check

Findings
None
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics
deepseek-harness, dsh, dsh-bundle, dsh-plugin, dsh-plugins, typescript

Related plugins

DeepSeek Harness
Score83

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.

☆ 393 ↓ 36.2K Memory
DeepSeek HarnessClaude CodeCodex Featured
Score81

memsearch

zilliztech/memsearch

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

☆ 2.6K ↓ 1.7K Memory
DeepSeek Harness
Score80

dsh-mnemon

dsh-external/dsh-mnemon

Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with three-tier memory out of the box.

☆ 393 ↓ 36.2K Memory
MCP ServerClaude Code
Score80

markdownify-mcp

zcaceres/markdownify-mcp

A Model Context Protocol server for converting almost anything to Markdown

☆ 3.0K ↓ 1.2K Memory