mneme Record

Name: mneme Record
Author: OnourImpram

作者：OnourImpram版本 4.1.0i★ –i在你的电脑上运行

注册名称io.github.OnourImpram/mneme

安装

概览

作者提供的说明（英文原文）

Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 搜索与 AI 记忆

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
注册中心没有列出需要填写的密钥。

你需要

npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "mneme": {
      "command": "npx",
      "args": [
        "-y",
        "mneme-mcp-server"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add mneme -- npx -y mneme-mcp-server

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "mneme": {
      "command": "npx",
      "args": [
        "-y",
        "mneme-mcp-server"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "mneme": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mneme-mcp-server"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 OnourImpram 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

星标数多于此分类中其他 7254 个服务器的 0%
发布到注册中心的时间比此分类中其他 7254 个服务器的 36% 更新
基础检查结果等于或优于此分类中其他 7254 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

mneme Record 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（4.1.0）于2个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。

有什么可以替代它？

同一分类中有：Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

作者：upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT今天更新

安装

Codebase Memory

作者：DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT20天前更新

安装

Exa

作者：exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT上个月更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

mneme Record

Vault-native memory for Claude Code. Markdown is ground truth.

Every session starts from zero. You re-explain the same architecture, the same constraints, the same decision you already settled yesterday, and the tools that promise to fix it mostly store your conversation history in opaque SQLite blobs and call an LLM every time you finish a session. The record of your own work ends up somewhere you cannot read, cannot grep, and cannot take with you.

mneme records what happened in each Claude Code session as plain markdown files in a directory you own (the vault) and indexes them with SQLite FTS5. The next session opens with a preflight block — today's headings, a git status summary, and the five most recently modified session documents — and the agent queries the index on demand through mneme_search.

Here is the file the Stop hook writes. The frontmatter, heading, and summary shape come from packages/mneme-cc-plugin/src/mneme_cc_plugin/hooks/stop.py and packages/mneme-core/src/mneme_core/distill/templates/summary-en.md; the contents below are illustrative.

---

id: session-2026-07-24 type: session created: 2026-07-24T09:12:41.087213+00:00 schema_version: 1

Sessions 2026-07-24

09:12 session a3f19c2e

transcript: ~/.claude/projects/mneme/a3f19c2e.jsonl

Session intent: make the retrieval guard fail on the negative probe too

Files touched

benchmarks/retrieval/regression_guard.py
benchmarks/retrieval/baseline.json

Tool activity (34 events, 08:41:02 → 09:12:38)

Edit: 11
Bash: 9
Read: 8

*Deterministic extractive summary (zero-LLM). Edit freely — this file is yours.*

pipx install mneme-cc-plugin && mneme install

That installs the plugin and registers the lifecycle hooks; mneme doctor verifies the result, and profiles and per-client installs are under Three-Tier Install. Claude Code registers six hook events; Codex and Antigravity map four. Any other MCP client (Kimi, Qwen, Cline, Cursor) gets the ten MCP tools through the open adapter, with no lifecycle hooks and no automatic capture.

What it stores is a file you can open. When a session has actually changed something in the vault, the Stop hook appends a timestamped ## HH:MM session block to vault/sessions/YYYY-MM-DD.md with type: session frontmatter, written atomically under a cross-process lock; mneme index rebuild reconstructs the FTS5 index over every markdown file in the vault, so the database is derived state you can delete.
Closing a session costs nothing and takes 2 ms. "No LLM call on the critical path" is enforced in CI rather than promised in prose. tools/spec_verify.py parses all six lifecycle hook modules and fails the build on any import of seven network-capable roots (anthropic, openai, requests, httpx, urllib.request, urllib3, aiohttp), and packages/mneme-cc-plugin/tests/integration/test_c3_no_network.py re-checks the full transitive import closure of the three hot-path hooks at runtime, where a static scan cannot see. The Stop-hook proxy benchmark measures 2 ms at p95 over 100 sessions against a 1000 ms ceiling: benchmarks/latency/p95_guard.py enforces that ceiling inside the same path-scoped benchmark workflow described below, and packages/mneme-cc-plugin/tests/unit/test_stop_performance.py re-checks it over 100 real Stop calls on every CI run, which carries no path filter.
Search quality cannot silently degrade. A pull request that drops production-FTS5 nDCG@5 more than 0.02 below the locked baseline (0.8006, reported as 0.801), drops Recall@10 more than 0.05 below 1.00, or fails the out-of-vocabulary negative probe fails the build — benchmarks/retrieval/regression_guard.py, run by .github/workflows/bench.yml on every pull request and every push to main that touches packages/mneme-core, packages/mneme-mcp, benchmarks/, or the workflow file itself.

Scope and limits

Those numbers come from the in-repo benchmark suite, seeded with MNEME_BENCH_SEED=42. Benchmark A uses a 500-document corpus. Benchmark E uses its default 300-document, 30-query fixture. Reproduce with make bench-all. Both figures above — the 0.801 and the 2 ms — carry the note that governs every figure in this README:

Note: All figures below are deterministic regression anchors computed on a seeded synthetic corpus; they are not real-world quality measurements (see ADR-012).

Retrieval claims follow the reachable path. The production mneme_search path is FTS5 BM25. The Python core contains an experimental feature-hashed lexical-vector backend and an RRF fusion protocol used by unit tests and synthetic benchmarks, but that backend is not wired into the MCP server or installer. Full-profile summarize and timeline can add gated local Graphiti and Neo4j fields. A true semantic embedding backend remains roadmap.

Privacy and network. Inline tag redaction at staging write with SHA256 audit log. Zero outbound network calls except opted-in compression LLM and optional local Neo4j. Compression happens in the background, opt-in, with a cost cap.

Temporal reasoning. The deterministic claim lifecycle (valid-from/to, supersedes, as-of queries, contradiction detection, temporal blame provenance time-travel) is built in on every profile — pure SQLite, no extra dependency. Graphiti export and LLM claim extraction remain optional and never run on the Stop or critical path.

Context Continuity Engine (opt-in). Checkpoints are plain markdown in the vault, zero-LLM, default off.

Obsidian is fully optional. A vault is simply a plain directory of markdown files. mneme requires no specific editor, no external application, and no Obsidian installation. You can work with your vault using grep, git, VS Code, or any text editor. The term "vault" is borrowed convention for a self-contained markdown directory, not a dependency on any particular tool. Because the vault is plain markdown, a user who already uses Obsidian can point it at the same directory and get rendered notes, backlinks, and graph-view navigation over the wikilinks mneme writes. The two tools coexist cleanly: mneme stores all derived state (indexes, staging, audit logs) inside a .mneme directory that Obsidian ignores as a dot folder, and mneme's indexer excludes the .obsidian settings folder from indexing, so neither tool disturbs the other. Obsidian is a convenient viewer and navigator for vault content. It is not part of mneme's capture, indexing, or retrieval path, and it must not be treated as an installation prerequisite.

The full shipped / gated / roadmap ledger is in Implementation Status; the capabilities mneme does not ship at all are listed under What 2.0 Does Not Ship Yet.

Status: 4.1.0 public release. Package, plugin, runtime, citation, and documentation version sources are kept in lockstep by tools/version_bump.py (18 sources including this line, verified in CI), so no single declared version can drift. Upgrading from an earlier line: docs/UPGRADING.md.

Tools

The MCP server registers ten tools. Every client that speaks MCP gets all ten; lifecycle hooks and automatic capture are a separate layer that only Claude Code, Codex, and Antigravity provide. The authoritative list is packages/mneme-mcp/src/tool_registry.ts.

Tool	What it does
`mneme_search`	FTS5 BM25 retrieval over the vault with Turkish casefold normalization, plus date, memory-type, and scope filters. Returns ranked hits and EvidenceCards carrying content hashes, trust, confidence, and the backend that actually ran.
`mneme_recall`	Retrieves indexed documents by session identifier, date range, and scope. Returns paths, titles, modification times, memory types, and optionally the full markdown body.
`mneme_write`	Atomically appends or replaces a markdown section in a vault file. Enforces vault path containment and redacts private spans before storage.
`mneme_summarize`	Groups FTS5 matches for a topic by vault directory within optional date and scope filters. Graphiti enrichment appears only when that optional local graph integration is configured.
`mneme_timeline`	Returns scope-restricted references for a subject in chronological order. Graphiti facts and bi-temporal filtering appear only when the optional local graph integration is available.
`mneme_prime`	Builds a token-budgeted preflight context bundle from recent sessions and topic-relevant matches. A caller session identifier enables per-session injection deduplication and full, keypoints, or reference formatting.
`mneme_propose`	Queues a redacted memory-edit proposal for the policy drain. The server does not apply the edit directly; durable categories always require human approval.
`mneme_checkpoint_list`	Lists recent Context Continuity Engine checkpoints from the active scope, newest first. Missing checkpoint state returns an empty list.
`mneme_working_set_load`	Loads salience-ranked working-set items from a Context Continuity Engine checkpoint. Unknown and out-of-scope anchors return the same neutral not-found result.

How mneme compares

Memory tools in the Claude Code and agent ecosystem make different trade-offs. The table below compares architectural capabilities across the dimensions mneme commits to, and it deliberately includes the rows where another tool leads. These cells describe design properties that are publicly verifiable from each tool's documentation. They are not a benchmarked ranking. For mneme's own reproducible numbers see Reproducible Numbers; for per-tool detail and an honest "where mneme is not the best fit" list see docs/COMPETITIVE.md.

Legend: ✓ built in · gated shipped, needs an opt-in dependency or flag · ~ partial · — not available · n/a the dimension does not apply.

Dimension	mneme	claude-mem	mem0	Letta	Zep	Supermemory
Plain-markdown store you can `git diff` and grep	✓	—	—	~	—	—
Built-in redaction with SHA256 audit	✓	—	—	—	—	—
Deterministic Stop capture, no LLM call	✓	—	n/a	n/a	n/a	n/a
Hybrid retrieval in the normal user path	~	~	~	~	✓	✓
Temporal claim lifecycle (valid-from/to, supersedes, blame)	✓	—	~	~	✓	~
Project and code graph (tree-sitter, PR-impact)	gated	~	—	—	—	—

| Adaptive token and

只显示了开头部分；其余内容请在仓库中阅读

mneme Record

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“搜索与 AI 记忆”中的其他服务器比较i

常见问题

替代选择

Context7

Codebase Memory

Exa

作者的 README

mneme Record

Sessions 2026-07-24

09:12 session a3f19c2e

Scope and limits

Tools

How mneme compares