dsh-mneme

🌏 简体中文 · English

🧬 给 LLM 装上会自我进化的记忆

dsh-mneme 是 DeepSeek Harness (DSH) 的跨会话记忆插件。它不只「存得下」，更「管得好」：后台自动去重合并、矛盾先冻结等你裁决、全程可回放审计、默认全离线，还支持导出成人可读的 Markdown。

Mneme（Μνήμη）源自希腊记忆女神 Mnemosyne。她掌管记忆与梦境——正如 autoDream 在后台默默巩固你的记忆库。

它解决什么问题

每次新开对话，AI 都像第一次认识你？

dsh-mneme 给 DeepSeek Harness 装上跨会话记忆。 你聊过的项目、提过的偏好、做过的决定，AI 都记得——即使关掉了窗口，下次打开还在。

但 dsh-mneme 的可信之处，恰恰在你看不见的后台。下面这些，才是它和「一个会存东西的插件」的本质区别。

为什么可以信任它

• 🧾 可回放、可追责 — 每次自动整理都留一张「决策凭证」：输入快照 + 决策明细 + 结果哈希，同样的整理可复现回放，不默默吞错、不留无法追溯的改动。
• ⚖️ 矛盾先冻结，等你裁决（可关）— 两条记忆打架时，不擅自替你做主。可疑冲突会挂起待审，状态页冲突队列里并排对比、一键裁决（保留 A / 保留 B / 仅标记），确认后才生效。复杂判断，人永远在线。
• 🔐 记忆按 agent 与工作区隔离（可关）— scopeEnabled 开启后，每条记忆标注由哪个 agent、在哪个工作区写入；检索时本会话作用域优先（命中加权，他 scope 降权仍可见）；strictScope 再进一步——显式声明收窄到他者作用域的记忆在检索/注入里完全不可见（载体自动标注只降权，不硬挡）。多 Agent、多项目互不串台。
• 🌙 夜深人静才动手（可关）— 空闲时自动分层归档：常看的留在热区、久不用的压成摘要、陈旧的彻底归档。记忆库越用越精炼，不膨胀。
• 🧠 本地语义检索，默认离线 — 自带本地 Embedding 与精排，不强求 API Key，网络断了也能检索。
• 📝 Markdown 双向同步 — 记忆就是本地 .md 文件，随时打开编辑；人工改动会被优先尊重，不会被机器覆盖。
• 💾 删对话 ≠ 删记忆 — 清空聊天窗口，已保存的记忆仍在（可配置）。

5 分钟上手

# 安装插件
dsh plugin --profile web add @modusensus/dsh-mneme
dsh web

装完即可用。想在 5 分钟内看到它的价值：

1. 聊：新开对话，跟 AI 聊几句关于你的偏好或手头项目（比如"我写代码更喜欢 4 空格缩进"）。
2. 等：关掉窗口，重开新对话。如果它还记得刚才的事，说明记忆已经写入。
3. 调：去「设置 → 记忆库设置」按需打开下面三个开关（见快速配置）。

快速配置（可选）

以上均在 DSH 设置面板 → 记忆库设置 中修改。完整配置见 配置章节。

记忆库落点建议

记忆库默认在 ~/.dsh/memory，天然在宿主 profile 作用域之外；但真实落点由 memoryDir 配置决定。若把它指进 profile 作用域（形如 …/profiles/<名字>/…），宿主清理或迁移 profile 时记忆库会被连带带走（#218 末楼记录的实际事故）。插件启动时检测到这种落点会打一条告警——只提示、不搬库。安全做法：memoryDir 保持在 profile 之外（默认值即可）；要迁移库 = 停止写入 → 复制整个目录 → 改配置指向新位置 → 重启。

一图看懂记忆闭环

  写入 ──► 质量过滤（无用信息先拦下）
    │
    ▼
  SQLite + 本地 Markdown 镜像
    │（空闲时）
    ├─ autoDream ：去重 / 合并 / 归档 / 修正 / 冲突冻结
    └─ Sleep Mode ：分层压缩 + 模式发现 + 关系补全（可关）
    │
    ▼
  召回（混合检索 + 精排）──► 注入会话上下文

界面预览

面板内置中英双语，跟随你的 DSH 界面语言显示。以下为中文截图，英文版请切至文末 English 段落。

记录、浏览与筛选你的记忆。

自动从记忆里提炼实体，构建带属性的关系图谱。

状态面板一眼看清向量索引、LLM 消耗与自动巩固记录。

检索、实体抽取与记忆巩固开关都在设置里一站式配置。

可选写保护 Token，以及本地化的反馈通道，让记忆库完全本地、可审计。

隐私承诺

• 数据只存在你的电脑本地，不上传任何服务器
• 记忆是 Markdown 文件，人类可读、可手工编辑
• 默认零网络依赖，不需要 API Key
• 无遥测、无分析、无远程日志

用在其他 AI 工具里（MCP）

插件自带零依赖 stdio MCP server（独立 npm 包 mneme-memory，bin 名 mneme-mcp），任何 MCP 客户端都能挂载记忆六件套（memory_save / memory_search / memory_list / memory_get / memory_update / memory_delete）。

前置条件（一次性）：

1. DSH 在运行且插件已安装（MCP 数据面走插件的独立 API 127.0.0.1:8790）
2. 在 DSH 面板「设置 → 外部访问 API」生成 token

各客户端挂载（<你的token> 替换为上一步生成的值）：

旧挂载兼容：已部署的 dsh-mneme-mcp + DSH_MNEME_TOKEN 写法继续有效（bin 与 env 变量均保留，无需迁移）。未全局安装 npm 包时，把 command 换成 npx 并追加参数 -p mneme-memory mneme-mcp（Claude Code/OpenCode 写进 args 数组，Codex 写 args = ["-p", "mneme-memory", "mneme-mcp"]）。配置细节与安全注意事项见完整文档。

不开 DSH 也能服务（独立服务 daemon）

dsh-mneme-serve 把记忆库跑成常驻数据面——DSH 关着，第三方集成（网页端桥接、脚本、自有面板）照样读写同一份记忆：token 与 DSH 面板/CLI 共用，路由与「外部访问 API」同源，端口被占直接报错（与 DSH 外部访问二选一）。第一期无 LLM（巩固/蒸馏仍属 DSH 宿主）；检索默认 local 嵌入（首次启动自动取件模型，--embed off 可关）。

npm i -g @modusensus/dsh-mneme
dsh-mneme-serve          # 默认 ~/.dsh/memory + 127.0.0.1:8790

社区适配器

社区项目把 mneme 接入更多平台——它们不是本仓库的一部分，兼容性由各自维护者跟进：

想被收录？在 Discussions 开帖介绍你的项目，或直接提 PR 补充本表。

文档

🗺️ 路线图

🧬 记忆基因 → 🛡️ 审计加固 → 💤 睡眠维护 → 🕸️ 召回融合与图谱 → ✨ 面板增强 → 🌡️ 自进化记忆 → 🕸️ 图谱增强

完整逐小版本说明见 CHANGELOG。

🧪 本地开发

cd dsh-mneme && npm install
npm test        # 1651 个测试
npm run stress  # 三轴线压测
npm run sync    # src → lib 同步

🙏 致谢

autoDream 的理念溯源（理念借鉴、实现原创）：

• Claude Code 的 Auto Dream（Anthropic，Memory 2.0）：理念源头——会话间隙由后台子代理整理记忆文件（去重、修矛盾、清衰减）。
• Sleep-time Compute: Beyond Inference Scaling at Test-time（UC Berkeley & Letta，arXiv:2504.13171）：Auto Dream「离线巩固」思想背后的学术脉络。
• cc-haha：早期实现思路的参照之一。

在上述工作之上，dsh-mneme 做了自己的工程发展：K-Means++ 聚类预分组、类型化决策清单（keep / merge / archive / conflict / update，及 sleep 侧 supersede / differentiate）与可回放的 sha256 摘要审计链（dream_runs / receipt_chain）。如有遗漏的灵感来源，欢迎提 issue 指出。

🧬 Give Your LLM a Memory That Evolves

dsh-mneme is a cross-session memory plugin for DeepSeek Harness (DSH). It does not just store your memories — it manages them: background deduplication and merging, conflicts frozen for your review, a fully replayable audit trail, offline by default, and export to human-readable Markdown.

Mneme (Μνήμη) comes from Mnemosyne, the Greek goddess of memory and dreams — just as autoDream quietly consolidates your memory store in the background.

What problem does it solve

Every time you start a new chat, the AI acts like it's never met you?

dsh-mneme gives DeepSeek Harness cross-session memory. Projects you've discussed, preferences you've mentioned, decisions you've made — the AI remembers them even after you close the window.

But what makes dsh-mneme trustworthy lives in the background you never see. These are the traits that set it apart from "a plugin that just saves things."

Why you can trust it

• 🧾 Replayable, accountable — every consolidation leaves a "decision receipt": input snapshot + decision detail + result hash. The same run reproduces the same outcome. No silent mis-merges, no untraceable changes.
• ⚖️ Conflicts freeze, you decide (opt-in) — when two memories contradict, it does not take sides for you. The suspected conflict is parked for review, compared side-by-side in the status-page conflict queue, and resolved with one click (keep A / keep B / mark reviewed). On hard judgments, a human stays in the loop.
• 🔐 Memories isolated by agent & workspace (opt-in) — with scopeEnabled, every memory is stamped with which agent wrote it and in which workspace; retrieval favors the current scope (weighted hits, out-of-scope demoted but visible); strictScope goes further — memories explicitly scoped to other agents/workspaces become invisible to search and injection (auto carrier labels are demoted only, never hard-blocked). Multiple agents and projects, zero cross-talk.
• 🌙 It works while you sleep (opt-in) — idle time triggers tiered archiving: frequent memories stay hot, stale ones compress to summaries, old ones archive. The store stays lean as it grows.
• 🧠 Local semantic search, offline by default — built-in local Embedding + reranking. No API key required; retrieval still works without a network.
• 📝 Two-way Markdown sync — memories are local .md files you can open and edit; human edits are respected, never clobbered by the machine.
• 💾 Delete the session ≠ delete the memory — clearing a chat window keeps what was saved (configurable).

5-minute quickstart

# Install the plugin
dsh plugin --profile web add @modusensus/dsh-mneme
dsh web

It works out of the box. To feel its value in five minutes:

1. Chat — start a session and tell the AI something about your preferences or a project (e.g. "I prefer 4-space indentation.").
2. Verify — close the window, open a new one. If it recalls what you said, the memory has landed.
3. Tune — open Settings → Memory Settings and flip the three switches below as needed.

Quick config (optional)

All of these live in DSH Settings → Memory Settings. Full config docs in the Configuration section (Chinese, bilingual file).

Where to put the memory library

The library defaults to ~/.dsh/memory, which is naturally outside any host profile scope; the actual location follows your memoryDir config. If it points inside a profile scope (a path like …/profiles/<name>/…), the library is taken away along with the profile when the host cleans or migrates it (an actual incident recorded in #218). The plugin logs a warning at startup when it detects such a location — advisory only, it never moves your data. Safe practice: keep memoryDir outside profiles (the default already is); to migrate, stop writing → copy the whole directory → point the config at the new location → restart.

The memory loop in one diagram

  write ──► quality filter (drop noise first)
    │
    ▼
  SQLite + local Markdown mirror
    │ (when idle)
    ├─ autoDream   : dedupe / merge / archive / fix / freeze-conflict
    └─ Sleep Mode  : tiered compression + pattern discovery + relation completion (opt-in)
    │
    ▼
  recall (hybrid search + rerank) ──► inject into the conversation

Screenshots

The panel is bilingual and follows your DSH interface language. English shots below; see the Chinese section for the localized UI.

Record, browse and filter your memories.

Entities are extracted from your memories, building a relation graph with attributes.

The status panel shows your vector index, LLM spend and consolidation activity at a glance.

Retrieval, entity extraction and consolidation toggles are all configured in one place.

Optional write-protect token and feedback channels for a fully local, auditable setup.

Privacy

• Data stays on your machine only, never uploaded
• Memories are Markdown files, human-readable and editable
• Zero network dependency by default, no API key required
• No telemetry, no analytics, no remote logging

Use it in other AI tools (MCP)

The plugin ships a zero-dependency stdio MCP server (standalone npm package mneme-memory, bin mneme-mcp). Any MCP client can mount the six memory tools (memory_save / memory_search / memory_list / memory_get / memory_update / memory_delete).

One-time prerequisites:

1. DSH is running with the plugin installed (the MCP data plane goes through the plugin's standalone API at 127.0.0.1:8790)
2. Generate a token in the DSH panel under Settings → External API

Per-client setup (replace <your-token> with the value from the previous step):

Legacy mounts keep working: dsh-mneme-mcp + DSH_MNEME_TOKEN remain supported (both the bin and env vars are preserved; no migration needed). If the npm package is not installed globally, use npx as the command with args -p mneme-memory mneme-mcp (an args array in Claude Code/OpenCode; args = ["-p", "mneme-memory", "mneme-mcp"] in Codex). Full config details and security notes: full docs (Chinese).

Serve memories without DSH (standalone daemon)

dsh-mneme-serve runs the memory store as a long-lived data plane — with DSH closed, third-party integrations (web-bridge tools, scripts, your own panels) still read and write the same memories: the Bearer token is shared with the DSH panel/CLI, routes mirror the external API, and a busy port is a hard error (pick either the daemon or DSH's external API, not both). Phase 1 is LLM-free (consolidation/distillation stay with the DSH host); retrieval defaults to local embeddings (runtime + model auto-provisioned on first boot, --embed off to disable).

npm i -g @modusensus/dsh-mneme
dsh-mneme-serve          # defaults: ~/.dsh/memory + 127.0.0.1:8790

Community adapters

Community projects that wire mneme into more platforms — not part of this repository; compatibility is tracked by their maintainers:

Want your project listed? Open a Discussion or send a PR adding a row to this table.

Docs

🗺️ Roadmap

🧬 Gene → 🛡️ Audit hardening → 💤 Sleep maintenance → 🕸️ Recall fusion & graph → ✨ Panel enhancement → 🌡️ Self-evolving memory → 🔐 Scope isolation

Full per-minor-version changelog in CHANGELOG.

🧪 Local development

cd dsh-mneme && npm install
npm test        # 1651 tests
npm run stress  # three-axis stress test
npm run sync    # src → lib sync

Acknowledgements

Provenance of the autoDream concept (ideas credited, implementation original):

• Auto Dream in Claude Code (Anthropic, Memory 2.0): the conceptual origin — a background sub-agent consolidates memory files between sessions (dedupe, resolve contradictions, prune decay).
• Sleep-time Compute: Beyond Inference Scaling at Test-time (UC Berkeley & Letta, arXiv:2504.13171): the academic thread behind the offline-consolidation idea.
• cc-haha: an early reference for the implementation approach.

On top of these, dsh-mneme adds its own engineering: K-Means++ cluster pre-grouping, a typed decision list (keep / merge / archive / conflict / update, plus supersede / differentiate on the sleep side), and a replayable sha256-digest audit chain (dream_runs / receipt_chain). If any source of inspiration is missing, please open an issue.

📜 License

MIT