supermemoryai / supermemory

查看原文 / View Original 编辑 / Edit

supermemoryai / supermemory

State-of-the-art memory and context engine for AI. And yes - you can use it as a company/personal brain. Docs · Quickstart · Dashboard · Discord 用于 AI 的最先进记忆与上下文引擎。没错，你可以将其用作公司或个人的“大脑”。文档 · 快速入门 · 仪表盘 · Discord

Supermemory is the memory and context layer for AI. #1 on LongMemEval, LoCoMo, and ConvoMem — the three major benchmarks for AI memory. We are a research lab building the engine, plugins and tools around it. Supermemory 是 AI 的记忆与上下文层。它在 LongMemEval、LoCoMo 和 ConvoMem 这三大 AI 记忆基准测试中均排名第一。我们是一家研究实验室，致力于构建围绕该引擎的插件和工具。

Your AI forgets everything between conversations. Supermemory fixes that. It automatically learns from conversations, extracts facts, builds user profiles, handles knowledge updates and contradictions, forgets expired information, and delivers the right context at the right time. Full RAG, connectors, file processing — the entire context stack, one system. 你的 AI 在对话结束后就会遗忘一切，而 Supermemory 解决了这个问题。它能自动从对话中学习、提取事实、构建用户画像、处理知识更新与冲突、遗忘过期信息，并在正确的时间提供正确的上下文。完整的 RAG（检索增强生成）、连接器、文件处理——整个上下文技术栈，尽在一个系统之中。

🧠 Memory: Extracts facts from conversations. Handles temporal changes, contradictions, and automatic forgetting. 🧠 记忆：从对话中提取事实。处理时间变化、逻辑冲突以及自动遗忘。

👤 User Profiles: Auto-maintained user context — stable facts + recent activity. One call, ~50ms. 👤 用户画像：自动维护的用户上下文——包含稳定事实与近期活动。单次调用响应时间约 50 毫秒。

🔍 Hybrid Search: RAG + Memory in a single query. Knowledge base docs and personalized context together. 🔍 混合搜索：单次查询即可同时实现 RAG 与记忆检索。将知识库文档与个性化上下文结合在一起。

🔌 Connectors: Google Drive · Gmail · Notion · OneDrive · GitHub — auto-sync with real-time webhooks. 🔌 连接器：支持 Google Drive、Gmail、Notion、OneDrive、GitHub——通过实时 Webhook 自动同步。

📄 Multi-modal Extractors: PDFs, images (OCR), videos (transcription), code (AST-aware chunking). Upload and it works. All of this is in our single memory structure and ontology. 📄 多模态提取器：支持 PDF、图像（OCR）、视频（转录）、代码（支持 AST 的分块）。上传即可使用。所有这些都整合在我们统一的记忆结构和本体中。

Use Supermemory 🧑‍💻

使用 Supermemory 🧑‍💻

I use AI tools: Build your own personal supermemory by using our app. Builds persistent memory graph across every conversation. Your AI remembers your preferences, projects, past discussions — and gets smarter over time. → Jump to User setup 我使用 AI 工具：通过我们的应用程序构建你个人的“超级记忆”。它能在每次对话中构建持久的记忆图谱。你的 AI 会记住你的偏好、项目和过往讨论，并随着时间推移变得越来越聪明。→ 跳转至用户设置

I’m building AI products: Add memory, RAG, user profiles, and connectors to your agents and apps with a single API. No vector DB config. No embedding pipelines. No chunking strategies. → Jump to developer quickstart 我正在构建 AI 产品：通过单一 API 为你的智能体和应用添加记忆、RAG、用户画像和连接器。无需配置向量数据库，无需嵌入流水线，无需分块策略。→ 跳转至开发者快速入门

Give your AI memory

为你的 AI 赋予记忆

The Supermemory App, browser extension, plugins and MCP server gives any compatible AI assistant persistent memory. One install, and your AI remembers you. Supermemory 应用程序、浏览器扩展、插件和 MCP 服务器可为任何兼容的 AI 助手提供持久记忆。只需安装一次，你的 AI 就能记住你。

The app: You can use supermemory without any code, by using our consumer-facing app for free. Start at https://app.supermemory.ai. It also comes with an agent embedded inside, which we call Nova. 应用程序：你可以通过我们面向消费者的免费应用程序使用 Supermemory，无需任何代码。访问 https://app.supermemory.ai 开始使用。它还内置了一个名为 Nova 的智能体。

Supermemory Plugins: Supermemory comes built with Plugins for Claude Code, OpenCode, OpenClaw, and Hermes. These plugins are implementations of the supermemory API, and they are open source! Supermemory 插件：Supermemory 内置了针对 Claude Code、OpenCode、OpenClaw 和 Hermes 的插件。这些插件是 Supermemory API 的实现，并且完全开源！

MCP - Quick install

MCP - 快速安装

npx -y install-mcp@latest https://mcp.supermemory.ai/mcp --client claude --oauth=yes

Replace claude with your client: cursor, windsurf, vscode, etc. Read more about our MCP here - https://supermemory.ai/docs/supermemory-mcp/mcp 将 claude 替换为你的客户端：cursor、windsurf、vscode 等。阅读更多关于我们 MCP 的信息：https://supermemory.ai/docs/supermemory-mcp/mcp

What your AI gets

你的 AI 将获得什么

ToolWhat it does
memorySave or forget information. Your AI calls this automatically when you share something worth remembering.
recallSearch memories by query. Returns relevant memories + your user profile summary.
contextInjects your full profile (preferences, recent activity) into the conversation at start. In Cursor and Claude Code, just type /context.
工具功能
memory保存或遗忘信息。当你分享值得记住的内容时，AI 会自动调用此功能。
recall通过查询搜索记忆。返回相关记忆及你的用户画像摘要。
context在对话开始时注入你的完整画像（偏好、近期活动）。在 Cursor 和 Claude Code 中，只需输入 /context。

How it works

工作原理

Once installed, Supermemory runs in the background: 安装后，Supermemory 将在后台运行：

  1. You talk to your AI normally. Share preferences, mention projects, discuss problems.
  2. 你像往常一样与 AI 对话。分享偏好、提及项目、讨论问题。
  3. Supermemory extracts and stores the important stuff. Facts, preferences, project context — not noise.
  4. Supermemory 提取并存储重要内容。事实、偏好、项目上下文——过滤掉噪音。
  5. Next conversation, your AI already knows you. It recalls what you’re working on, how you like things, what you discussed before.
  6. 下次对话时，AI 已经了解你。它能回忆起你正在做什么、你的偏好以及之前讨论过的内容。

Memory is scoped with projects (container tags) so you can separate work and personal context, or organize by client, repo, or anything else. 记忆通过项目（容器标签）进行划分，因此你可以将工作与个人上下文分开，或按客户、仓库或其他任何方式进行组织。

Build with Supermemory (API)

使用 Supermemory 构建 (API)

If you’re building AI agents or apps, Supermemory gives you the entire context stack through one API — memory, RAG, user profiles, connectors, and file processing. 如果你正在构建 AI 智能体或应用，Supermemory 通过单一 API 为你提供完整的上下文技术栈——包括记忆、RAG、用户画像、连接器和文件处理。

Install: npm install supermemory (or pip install supermemory) 安装：npm install supermemory (或 pip install supermemory)

Quickstart (JS/TS): 快速入门 (JS/TS):

import Supermemory from "supermemory";
const client = new Supermemory();

// Store a conversation
await client.add({ 
  content: "User loves TypeScript and prefers functional patterns", 
  containerTag: "user_123", 
});

// Get user profile + relevant memories in one call
const { profile, searchResults } = await client.profile({ 
  containerTag: "user_123", 
  q: "What programming style does the user prefer?", 
});

Quickstart (Python): 快速入门 (Python):

from supermemory import Supermemory
client = Supermemory()

client.add(
    content="User loves TypeScript and prefers functional patterns",
    container_tag="user_123"
)

result = client.profile(container_tag="user_123", q="programming style")
print(result.profile.static) # Long-term facts
print(result.profile.dynamic) # Recent context

Supermemory automatically extracts memories, builds user profiles, and returns relevant context. No embedding pipelines, no vector DB config, no chunking strategies. Supermemory 会自动提取记忆、构建用户画像并返回相关上下文。无需嵌入流水线，无需向量数据库配置，无需分块策略。

Framework integrations: Drop-in wrappers for every major AI framework (Vercel AI SDK, Mastra, etc.). 框架集成：为所有主流 AI 框架（Vercel AI SDK、Mastra 等）提供即插即用的封装。

← 返回新闻列表 / Back to news list