Atlaso Memory

ai.atlaso由 atlaso.ai 发布官方发布者v1.0.2更新于 Oct 26, 2026

Atlaso, the AI memory layer: one shared, persistent memory for every AI tool you connect.

已验证Streamable HTTP可网页运行效率与工作流知识与记忆

概览

AI 生成的概览

托管式记忆层，让任意 MCP 客户端共享一份持久记忆，保存决策、偏好与上下文，并在不同 AI 工具间延续。

可以做什么
  • 按查询检索已存记忆，返回排序后的笔记列表，并标注该记忆是已确定还是有争议
  • 保存持久笔记，如决策、偏好或注意事项，并标注极性
  • 按时间倒序列出最近的记忆
  • 按 id 永久删除某条记忆
  • 查看连接状态、已存与待处理记忆数量以及记忆健康评分
适用场景
适合同时使用多个 MCP 客户端或编码工具、希望上下文、决策和偏好能在工具之间延续，而不必在每个对话里重新说明的场景。
运行要求
需要支持 Streamable HTTP 的远程 MCP 客户端；连接托管端点并通过 OAuth 2.1（含动态客户端注册）授权，无需粘贴 API 密钥，也无需自行部署。终端工具可选安装 CLI 以实现自动召回与记录。免费版限一台设备和一个工具，更多需付费。
安装前请注意
forget 工具会永久删除记忆且无法撤销。记忆存放在第三方托管服务上，助手保存的内容会离开本机；README 称会清除敏感信息并加密传输与存储，但仍应留意被记住的内容。付费方案为每月 10 或 25 美元。可选的安装脚本会创建账户并关联本机。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Atlaso Memory，将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/ai.atlaso%2Fmcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "atlaso-memory": {
      "type": "http",
      "url": "https://mcp.atlaso.ai/mcp"
    }
  }
}

README

Atlaso — remote MCP server

Atlaso is an AI memory layer: one shared, persistent memory across every AI tool you connect.

Tell it once in one tool, and it's already there in the next. Atlaso recalls the context that matters before each turn and captures the durable facts after — your decisions, your preferences, and where you left off.

This repository documents Atlaso's hosted MCP server. Atlaso is a managed service, so there is nothing to self-host and no server code here — you connect to the endpoint below and authorize in your browser.

  • Endpoint: https://mcp.atlaso.ai/mcp
  • Transport: Streamable HTTP
  • Auth: OAuth 2.1 with dynamic client registration — your MCP client walks you through it; there are no API keys to paste
  • Website: https://www.atlaso.ai
  • Docs: https://docs.atlaso.ai

Why this exists

Claude Desktop, Zed, Cline and other MCP clients have no memory of their own that reaches your coding tools. This hosted server gives any MCP client the same memory your coding tools share: decisions made in long chats, research and notes, preferences that should follow you. Memory works when the model calls the tools (remember, recall, forget); a skill can make that routine. Add https://mcp.atlaso.ai/mcp as a connector and sign in. Claude Desktop · Any MCP tool

Connect

Any MCP client that supports remote servers can connect. Add https://mcp.atlaso.ai/mcp as a connector and authorize in the browser when prompted.

Claude Desktop / claude.ai — Settings → Connectors → Add custom connector → paste the endpoint → Connect → authorize.

Cursor, VS Code, and other MCP clients — add it as a remote MCP server:

json
{  "mcpServers": {    "atlaso": {      "url": "https://mcp.atlaso.ai/mcp"    }  }}

Terminal-based tools (Claude Code, Codex, OpenCode, Antigravity) get a richer integration than MCP alone — automatic recall before each turn and automatic capture after, via hooks. One command sets all of them up:

bash
curl -fsSL https://atlaso.ai/install.sh | bash    # macOS / Linuxirm https://atlaso.ai/install.ps1 | iex           # Windows

That installs the atlaso CLI, links the machine (creating your account if you don't have one), then asks which of your AI tools should share the memory.

Tools

ToolWhat it does
recall(query, limit=5)Search your memory for notes relevant to query. Returns a ranked list of {id, content}. Read-only.
remember(text, polarity)Save a durable note — a decision, preference, or gotcha. polarity is one of positive, open, cautionary, negative. Returns the new id.
recent(limit=10)List the most recent memories, newest first. Read-only.
forget(id)Permanently delete a memory by id. Destructive and not undoable.
status()Connection state, how many memories are stored and pending, and your memory health score. Read-only.

Every recall carries a verdict on whether a memory is settled or contested, so the model isn't acting on shaky context.

Memory scopes

Memories are either personal (they follow you everywhere) or project (scoped to the repository or workspace you were in). Both are recalled automatically in the right place — you don't manage scopes by hand.

Privacy

Secrets are scrubbed before anything is stored. Data is encrypted in transit and at rest. Your memory is never used to train AI models and never sold. On the free plan it is never sent to any LLM at all. You can delete any single memory, or your whole account, at any time.

Pricing

Free for one device and one tool. Pro is $10/month for unlimited devices and tools sharing one memory, plus Ambient Memory, background enrichment, Ask your memory, and JSON export. Build is $25/month and adds a developer memory API.

Registry

Listed in the official MCP Registry as io.github.imashishkh21/atlaso. The server.json in this repository is the published manifest.

Atlaso is a product of Atlaso Labs Inc. This repository is documentation for the hosted service; the service itself is not open source.

来源：README.md，提交 050849e

工具

0
该服务器需要登录，因此 SourceWeft 无法在没有账号的情况下读取其工具，也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

2
  1. v1.0.2最新Oct 26, 2026
  2. v1.0.1Sep 16, 2026

评分

已满足适用检查项的 75%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。

其他 Atlaso 集成

Atlaso

由 GitHub 账号 imashishkh21 发布

Atlaso 是一个本地开源记忆服务器，让 AI 助手借助本地 SQLite 数据库获得持久化回忆能力。

STDIO仅桌面
数据库尚未验证Oct 25, 2026