Persistent conversation memory for DeepSeek Harness: memory tab, automatic AI naming, per-AI privacy isolation, sidebar AI names, and automatic experience archiving. A static profile plugin available in every preset without disappearing on restart.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:hmlyx/dsh-memory
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
让 DeepSeek Harness 里的 AI 拥有持久记忆：记忆标签页、自动命名、多 AI 隐私隔离、侧栏 AI 名、经验自动归档。装上即生效，重启不消失，任何预设可用。
👤 功能一览
| 功能 | 说明 |
|---|---|
| 📁 记忆标签 | 对话视图新增「记忆」标签：总开关、改名、文件浏览 |
| 🏷️ 自动命名 | 名字库随机分配 AI 名（50 个，不重复，可询问） |
| 🔒 隐私隔离 | 全局/简要记录按 AI 私有，其他 AI 不可查看 |
| 📤 经验共享 | 经验对其他 AI 开放只读，解决过的问题可复用 |
| 👥 侧栏 AI 名 | 一键让所有会话侧栏显示各自 AI 名 |
| 📝 memory_record | AI 用 memory_record 工具随时归档 global/shared/brief/event/experience |
安装：仓库放入 ~\.dsh\profiles\web\node_modules\dsh-memory\，在 ~\.dsh\profiles\web\package.json 的 dependencies 加 "dsh-memory": "3.0.0"、dsh.profile.bundles 加 "dsh-memory"，重启 DeepSeek Harness。回滚：删掉那两处引用（备份 package.json.bak-memory）。
数据位置
记忆文件在 对话记忆\（默认探测：会话工作区下，只接受真实存在的目录），.memory-state.json 持有各会话名字/开关状态——与旧动态插件兼容，数据不迁移、不丢失。
🤖 给 AI 的使用说明
memory_record工具：kind = global / shared / brief / event / experience；全局/简要私有，经验开放只读，共享/重大事件所有人可见；- 主动义务：解决问题/学技巧当场写经验；完成任务/开启新任务前总结带标题经验；
- systemPrompt 注入：AI 名 + 记忆义务（无需用户提醒）；
- 侧栏改名：会话结束自动还原原始标题。
结构
| 文件 | 作用 |
|---|---|
index.mjs |
Host 半：/__memory/* 接口、memory_record 工具、自动命名、侧栏 AI 名、systemPrompt 注入（头部有接口目录） |
client.js |
Client 半：「记忆」标签 UI（头部有功能目录） |
cordis.patch.yml |
把 dsh-memory 插件行插入 profile 组成 |
接口
GET /__memory/state?session=<id>— 状态与文件列表GET /__memory/read?session=<id>&name=<file>— 读一个记忆文件POST /__memory/set-master | set-sidebar-all | set-name | set-enabled | set-autoname | set-sidebar-name— 各开关/改名
License
MIT
Links
More in this category
vectorize-io/hindsight#coding-agents★ 49727
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
volcengine/OpenViking#examples/dsh-memory-plugin★ 39942
OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.
agentscope-ai/ReMe#dsh★ 3594
Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.
zilliztech/memsearch#MemSearch★ 2745
Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.
vshulcz/deja-vu#extensions/dsh★ 1200
Reads the session files thirty-three other coding agents on this machine already wrote — Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more — including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).
adoresever/graph-memory★ 649
Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.