Skip to content
This page is not translated yet — showing the original. We never ship machine translation as a placeholder.
Needs a toolchainApache-2.0⚪ Tested only

Mem0

In one line:Mem0 是一个给要做长期对话记忆的开发者用的开源记忆层,能把跨会话记住的事接进应用。

Mem0 是一个给要做长期对话记忆的开发者用的开源记忆层,能把跨会话记住的事接进应用。

Official source

We host and mirror nothing — the official page is the source of truth.

No hotlinkable official icon; showing a generated placeholderM Mem0https://github.com/mem0ai/mem0Open official page
Official sourceYou are leaving AIWorksWell for Mem0. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.

Install prompt

Copy it, paste it into your AI (Claude Code, Codex, ChatGPT…), and it installs and verifies for you.

48 lines
我需要你帮我在我的机器上安装并运行一个软件。

【软件信息】
名称:Mem0
用途:Mem0 是一个给要做长期对话记忆的开发者用的开源记忆层,能把跨会话记住的事接进应用。
官方来源:https://github.com/mem0ai/mem0
许可:Apache-2.0
Scroll inside the box with your mouse wheel — copying still gives you the full prompt1479 chars

Copy → paste into your own AI → it installs for you

Contact the original author (Mem0)

Bugs in the software itself go to the author's own official channel — that is where they actually receive them. We pass things on; we do not answer for the author.

Install failed?

Paste the raw error — once triaged and verified it is written back here, so the next person's AI avoids it. No login needed.

About this entry

What it is

Mem0 是开源的 AI 记忆层(Apache-2.0 许可),负责跨会话记住与该忘的东西。来源:https://mem0.aihttps://mem0.ai

  • 一次模型调用抽取事实,只追加不覆盖
  • 语义、关键词、实体三路检索融合,另带时间推理
  • 开源 SDK 与托管平台两条路,分数口径不同

Getting it running

主推「复制提示词」——粘贴给你的 AI(Claude Code / Codex / ChatGPT)代装。人工兜底:pip 装 SDK,配上模型与向量库,跑一次写入记忆再加一次带记忆的问答。验证:第二次提问能取回第一次写入的事实。来源:https://docs.mem0.ai/https://docs.mem0.ai/

以上坑来自 https://mem0.aihttps://mem0.ai 与它的官方文档。

来源与署名

Mentioned from:GitHub · 原作者 Mem0(Apache-2.0)。

Summary for AI

Mem0 夹在应用与大模型之间,负责把"该记住的事"存起来并在下次对话里取回。官方 2026 年的新算法改成单次只追加的抽取——一次模型调用,不做改写与删除,记忆只累积;检索侧同时跑语义、BM25 关键词与实体匹配三路并融合,还带时间推理。开源 SDK 与托管平台的分数不同,官方明确说托管版有闭源优化。

A self-contained answer paragraph — this is the part AI search quotes. · Page reviewed 2026-10-22

FAQ

它替我把对话全存下来吗?

不是。它抽事实来存,一次调用只追加不覆盖。

开源版与托管版差在哪?

官方说托管版另有闭源优化,开源版效果方向相同但数字不同。

Pitfalls / known issues

All recorded from real installs, and injected into the prompt above.

  • •抽取质量依赖你接的模型,小模型容易抽出噪声事实。
  • •开源版与官方榜单数字不同,别拿托管版分数当自建预期。
  • •它只追加不删除,记忆会一直长,要自己规划清理。

You might also like

We store, mirror and repackage nothing. Every install path points to the author’s own official page.

Nothing here has been reviewed by an app store. Judge the source and licence yourself; you install at your own risk.