Gnosis Memory

安装

选择你使用的 AI 应用，然后复制设置。

通过 3/3 项检查 · 你的提问会经过开发者的服务器（gnosismemory.com） · ✓ 命令已检查 2026年11月13日

claude mcp add --transport http --scope user memory https://gnosismemory.com

{
  "mcpServers": {
    "memory": {
      "url": "https://gnosismemory.com"
    }
  }
}

{
  "servers": {
    "memory": {
      "type": "http",
      "url": "https://gnosismemory.com"
    }
  }
}

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档，检查于 2026年11月10日。

通过互联网连接，适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月10日 报告的完全一致。这些内容由作者撰写，不是我们写的；我们以纯文本形式显示。

• init_core_memories

  Run ONCE at conversation start. Loads behavioral prefs + recent context. Previews carry a 'complete' flag: true = full content shown; false = opening only, memory_retrieve(id) for the rest. After init, use memory_search for specific queries. Shared collections -> 'collections' fi

• memory_add

  Store a memory. Several memories in one call -> memories=[{content, topics, ...}]; top-level topics then apply to every item. BEFORE params decide: (1) TYPE? (2) what search finds this later? (3) happened, or aspirational? (4) WHO must act on it? TYPE by example: "User prefers da

• memory_add_batch

  Store multiple memories at once. Same rules as memory_add, applied per item. SHAPE: one ITEM here == one memory_add call. Same field names, same meaning. The ONLY difference is the container: memory_add takes them as flat parameters, this takes a list of objects. An item object b

• memory_search

  Search memories by relevance. Up to 32 results. Query = ALL nouns from the user's message, not just the main one (ranking is automatic). "How does the app cache API calls?" -> "app cache api calls" complete=false results are truncated -> memory_retrieve(id) for full content. Auto

• memory_deep_search

  Broad search for a FULL sweep -- every hit on a topic (e.g. before memory_consolidate), not a conversational lookup (that is memory_search). Up to 128 results; requires 2+ keywords ("python" alone = too broad). Scores: 30+ excellent, 20+ good, <20 weak. Full sweep of a topic inte

• memory_retrieve

  Get full content by ID. Use when search returned complete=false. Batch: memory_retrieve(["id1","id2"]). Skip if complete=true (preview is already full).

• artifact_write

  Store or update a long document (markdown, JSON or text) behind a pointer memory. For agents.md, skills.md, assertions.md, a project plan: anything past one memory's 768-token cap. CREATE: name ("assertions.md"), summary (the pointer memory: what the document is and why; search f

• artifact_read

  Read an artifact by its pointer memory id (memory_retrieve on a pointer shows an "artifact" block with head_rev_id and outline). Bodies over 40,000 characters return the outline: read a section (heading path or JSON pointer) or page=0,1,... Returns rev_id; pass it as base_rev_id

• artifact_history

  List the revisions of an artifact (rev_id, parent, seq, time, author, pinned) and its heads. conflict=true means divergent heads to merge.

• artifact_pin

  Pin a revision so retention thinning never removes it (pinned=false unpins).

• artifact_delete

  Delete an artifact: every revision and its pointer memory. Permanent. confirm must equal the artifact name. memory_delete refuses a pointer; use this.

• artifact_orphans

  List artifact revisions whose pointer memory is gone (a delete on one replica racing a save on another). Nothing is auto-deleted; export includes them.

• memory_edit

  Edit a memory. Provide only what changes; omitted fields untouched. Modes: 1. Content replace (content [+topics/macro_topics]): full rewrite, re-embeds. Do it the instant the user corrects a memory ("actually..."). 2. Metadata patch (topics/type/expiry, no content): type/expiry a

• memory_delete

  Delete memories by ID. Permanent. memory_delete(["id1","id2"]). Delete by filter: memory_search first, collect ids, then delete.

• memory_consolidate

  Create/replace a topic's executive summary. One per topic; replacing archives the old (restorable). WARNING: a bad summary poisons every future session. Do NOT consolidate from partial knowledge. BEFORE calling: (1) memory_deep_search the topic; (2) read 20+ memories, not preview

• task_feed

  Recently-changed tasks, chronological (not ranked). For "what needs attention?" / "what changed?". Find tasks by content -> memory_search. Each: preview, progress [done,total], status, topics, collection. Default 32, max 500. Fan-out: no collection -> personal + all your collecti

• collection_manage

  Manage shared collections (multi-user memory folders). list: your collections + invites. create. update: rename (display only; slug/keys unchanged). delete: owner only, 2-step -- call without confirm to see impact + token, repeat with confirm:" ". Permanent. members: who's in it.

• agent_manage

  Manage agents (NAMESPACES under your account, sharing your token). An agent is a namespace, never a holder of key material: all crypto is the ACCOUNT's, and an agent id is never an input to a wrap, a seal or a KEK. Agents organise and scope what is visible; they do not own encryp

• signal

  Inter-agent signals -- sticky notes pointing at a memory_id. Both parties must share a collection. send: post to a teammate. check: read pending (removes nothing). ack: mark handled -- stamps delivered_at, the row stays, NOTHING IS DELETED. ACK MEANS CLOSED, NOT DONE: it asserts

• message

  Direct inter-agent text that DIES ON ACK. Use for receipts, FYIs and short replies; use signal to point at a memory. send/check/ack. LOSABLE BY DESIGN: the first session of the recipient name to ack deletes it for every session of that name, an unacked message is deleted at expir

• account

  Account state + billing. Returns URLs only -- user clicks to pay; never charges silently. Pick by intent: "what plan am I on?" -> info (tier, subscription, capabilities, upgrade/downgrade SKUs; permanent tiers og/truebeliever/ogdev cannot downgrade) "what can I buy?" / "how much

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13日

• ✓ 通过

  作者与仓库一致

  注册名称已通过域名 gnosismemory.com 验证（注册中心会核实域名所有权）

• … 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

• ✓ 通过

  端点有响应

  在 116 毫秒内响应（HTTP 200）

• – 不适用

  使用 OAuth 登录

  无需登录

• ✓ 通过

  工具描述中没有隐藏指令

  已读取 21 个工具描述，未发现针对 AI 的隐藏指令

用户评价

还没有评价

用 Google 登录后写评价

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 6051 个服务器的 0%
• 发布到注册中心的时间比此分类中其他 6051 个服务器的 15% 更新
• 基础检查结果等于或优于此分类中其他 6051 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。

同类别的其他选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：↓ 每周下载量i★ 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

Up-to-date docs for AI agents

作者：upstash·广泛使用·↓ 125万/周·★ 6.5万·昨天更新

电脑或云端

安装

Codebase Memory

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

作者：DeusData·广泛使用·↓ 1.7万/周·★ 4.9万·27天前更新

在你的电脑上运行

安装

Ruflo

Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.

作者：ruvnet·广泛使用·↓ 7.4万/周·★ 8.2万 整个仓库的星标·今天更新

在你的电脑上运行

安装

作者的 README

仓库中没有找到 README