dsh-memory-lite
On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.
给 DeepSeek Harness 的按需记忆库：会话日志提炼成分层 markdown（总览、索引与分主题明细），mem_query 只回命中条目而非整份索引。不每轮注入、零依赖，每条记忆都保留指回原对话的溯源标记。
How to install
dsh plugin add github:MiHjy12138/dsh-memory-lite About
dsh-memory-lite 记忆插件都在比「记得多」，它只比「查得省」。 你的 agent 不是记性差，是记忆太贵：**每轮注入记忆，就是每轮重发计费；读一次索引，就是上万字符全程占位。** 这个项目只优化一个数——**查一次记忆 11,819 → 738 字符（省 92%）**。 为此它刻意**不做**那些要你每轮付钱、或每轮维护的东西： 不自动注入 · 不建向量库 · 不起后台进程 · 不做知识图谱 · 不做侧栏面板 · 零依赖 留下的只有三样：**本地 markdown · 一个查询工具 · 一份能人工核对的溯源**。 作者的话： DSH本身的架构极其轻便： 一 · 基线上下文：~\.dsh\AGENTS.md，系统提示中出现 Instructions from: ~/.dsh/AGENTS.md 二 · 引用快照：@deepseek-ai/dsh-session-reference，输入框 @ 可选历史会话 三 · 索引查询：session-query-sqlite + dsh-tool-session-query，搜「记忆」跨会话命中 本插件只是在此基础上做了个小扩展。让记忆和索引更加顺畅，全程DSH自己搞的，我只负责提灵感。所以有什么问题即时反馈，会改的(๑˃ᴗ˂)ﻭ 框架核心：三条不变量 整套设计只为守住这三条。功能可以加，**这三条破了就不成立**。 | # |…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-09-17
- Created
- 2026-09-17
Links
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
- agent-memory, ai-agent, cli, context-engineering, deepseek-harness, dsh-plugin, knowledge-base, llm, long-term-memory, markdown, memory, nodejs, token-efficiency
Related plugins
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.
memsearch
zilliztech/memsearch
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
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.
markdownify-mcp
zcaceres/markdownify-mcp
A Model Context Protocol server for converting almost anything to Markdown