Mmcp.market

Mneme Memory MCP server

by modusensus·io.github.modusensus/mneme-memory·v0.1.1

Cross-session memory for AI coding agents via six tools; local-first SQLite store.

A86/100grade A
What users say
No reviews yet
Be the first
Safety scan
A86/100

full report

Adoption
Growing

119 stars

Reviews

Write one

Nobody has reviewed Mneme Memory yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Mneme Memory tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identitynamespace and repository owner differ4/10
Overall 86/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Mneme Memory repository's README, as published. We do not edit it. Read it on GitHub

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。

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。

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y mneme-memory on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mneme-memory -- npx -y mneme-memory
Add to Cursor

Mneme Memory: common questions

Is Mneme Memory MCP server safe?
Yes, by our scan: it is graded A (86/100). Read the Mneme Memory safety report
How do I install Mneme Memory?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Mneme Memory need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Mneme Memory maintained?
The last commit was in the last day (2026-09-23). The latest release is v0.1.1.
What can I use instead of Mneme Memory?
Servers from other publishers that do the same job: SentinelOne MCP server, MCP Server and Kagura Memory Cloud MCP server. Compare all Mneme Memory alternatives.

Alternatives to Mneme Memory

Same job from other publishers: the closest match first, then the best rated.

All Mneme Memory alternatives →
  • SentinelOne MCP
    Every SentinelOne v2.1 management endpoint, plus an offline SQLite store and cross-entity analytics
    B
  • MCP Server
    Typed record store + hybrid search over MCP: deterministic lookups + semantic memory, per-customer.
    B
  • Kagura Memory Cloud
    Persistent memory for AI assistants: store, search, and connect knowledge across conversations.
    A
  • MCP
    Generate App Store and Play Store screenshots from your coding agent, at exact store sizes.
    B
  • knowmind
    AI agent memory & knowledge graph, hosted in Germany (GDPR). Recall, relations, store via MCP.
    B

More from modusensus →