dsh-auto-memory
原生实现 Claude Code 式自动记忆:类型化记忆文件(user/feedback/project/reference)+ 自动注入系统提示词的 MEMORY.md 索引,无记忆时零提示词占用;memory_write/read/list/delete 遵循 Claude Code 写入规则(查重更新、相对日期转绝对、交叉链接);项目级与用户级双层作用域,跨进程文件锁与孤儿锁自愈,记忆为磁盘纯 Markdown,无外部服务、无 embedding。
- 形态
- Plugin 插件
- 安装
- npm 包安装
- 需要密钥
- 是
- 近月下载
- 1 万
- 最近推送
- 3 天前更新
项目说明
From README
dsh-auto-memory English 中文 Your dsh agent forgets everything you tell it.Every.Single.Session.Fix it with one command.Claude Code-style persistent memory for DeepSeek Harness — native, zero servers, zero embeddings, zero setup.
Say "Remember: I'm a Python backend engineer preparing for interviews" today — open a brand-new session tomorrow, ask "what do you know about me?" , and it remembers .--- Highlights 1.
x — trustworthy memory + measured end-to-end : consolidation products are born candidate with verbatim evidence quotes; only you can grant verified ; disputed memories are never re-injected; every write passes an injection-pattern guard at the store choke point.
And it's measured: four evaluation layers (deterministic / recall / consolidation / end-to-end) plus a LongMemEval-S alignment run — including an honestly published off-target score.Full history: CHANGELOG.md · Release
Original description
Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.
安装方式
npm 包安装 · 需要额外配置密钥
dsh plugin --profile web add dsh-auto-memory安全能力
静态扫描源码得到的权限画像 —— 回答的是「它要动什么」，而不是「它好不好」
- 写入文件
- 读取文件
- 访问网络
未发现已知红线（明文传输、安装期执行代码、凭据外传等）。
能力与红线来自 awesome-dsh-plugin 的静态扫描结果（CC0 公有领域），本站未逐行复核源码； 它只覆盖能被静态识别的模式，不等于安全审计结论。
为什么是这个分数
近 3 天仍在推送；README 给出了可直接复制的安装命令；运行前需要准备 API Key 或环境变量；近月 npm 下载 10222 次，star 不多但真在被使用。
- 维护活跃
- 96
- 实用度
- 94
- 生态热度
- 80
- 上手便捷
- 74
- 信号质量
- 100
- 数据置信度
- 100%
相关插件
mnemon
mnemon-dev/mnemon
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
EverOS
EverMind-AI/EverOS
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
OpenViking
volcengine/OpenViking
面向 DeepSeek Harness 的 OpenViking 记忆与上下文插件：pre-step 自动召回与画像注入、会话捕获、`viking://` URI 防护，以及对接 OpenViking 服务端的 recall/write 记忆工具。