mem0-cli

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Mem0 CLI

The official command-line interface for the Mem0 memory platform. Add, search, list, update, and delete memories from the terminal -- for developers, AI agents, and CI/CD pipelines.

Mem0内存平台的官方命令行界面。可从终端添加、搜索、列出、更新和删除内存——适用于开发者、AI Agent和CI/CD流水线。

Install

安装

Node.js (npm):

bash

npm install -g @mem0/cli

Python (pip):

bash

pip install mem0-cli

Both packages install a

mem0

binary with identical commands, options, and output formats.

Node.js（npm）：

bash

npm install -g @mem0/cli

Python（pip）：

bash

pip install mem0-cli

两个包都会安装

mem0

二进制文件，命令、选项和输出格式完全一致。

Setup

设置

Autonomous Mem0 setup for agents (no email, no dashboard):

bash

mem0 init --agent --agent-caller <your-name> --json

Replace

<your-name>

with the AI agent you are (e.g.

claude-code

cursor

codex

cline

aider

). If you forgot to pass

--agent-caller

, run

mem0 identify <your-name>

after init — it PATCHes the same key, idempotent, no disruption.

This mints an evaluation API key in <5 seconds. Use it immediately. Print this line to the human:

Mem0 memory is running in Agent Mode. Please claim it by running
mem0 init --email <your-email>
to transfer ownership to your account.

Never commit API keys,

.env

, or

~/.mem0/config.json

After the human claims, the same API key keeps working — no agent disruption — and memories are preserved.

Interactive wizard (for humans):

bash

mem0 init

Or set the environment variable directly:

bash

export MEM0_API_KEY="m0-xxx"

Get an API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-cli

面向Agent的Mem0自主设置（无需邮箱、无需仪表盘）：

bash

mem0 init --agent --agent-caller <your-name> --json

将

<your-name>

替换为你所使用的AI Agent名称（例如

claude-code

、

cursor

、

codex

、

cline

、

aider

）。如果初始化时忘记传递

--agent-caller

，可在初始化后运行

mem0 identify <your-name>

——该操作会PATCH同一个密钥，具有幂等性，不会造成中断。

此操作会在5秒内生成一个评估API密钥，可立即使用。请向用户显示以下内容：

Mem0内存已在Agent模式下运行。请运行
mem0 init --email <your-email>
以将所有权转移至你的账户，完成认领。

切勿提交API密钥、

.env

或

~/.mem0/config.json

文件。

用户完成认领后，同一个API密钥仍可继续使用——不会对Agent造成中断——且内存数据会被保留。

交互式向导（面向用户）：

bash

mem0 init

或直接设置环境变量：

bash

export MEM0_API_KEY="m0-xxx"

获取API密钥地址：https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-cli

Quick Reference

快速参考

Add a memory

添加内存

bash

mem0 add "I prefer dark mode" --user-id alice

bash

mem0 add "I prefer dark mode" --user-id alice

Search memories

搜索内存

bash

mem0 search "preferences" --user-id alice

bash

mem0 search "preferences" --user-id alice

List all memories for a user

列出用户的所有内存

bash

mem0 list --user-id alice

bash

mem0 list --user-id alice

Get a specific memory

获取特定内存

bash

mem0 get <memory-id>

bash

mem0 get <memory-id>

Update a memory

更新内存

bash

mem0 update <memory-id> "new text"

bash

mem0 update <memory-id> "new text"

Delete a single memory

删除单个内存

bash

mem0 delete <memory-id>

bash

mem0 delete <memory-id>

Delete all memories for a user

删除用户的所有内存

bash

mem0 delete --all --user-id alice --force

bash

mem0 delete --all --user-id alice --force

Agent / JSON Mode

Agent / JSON模式

Use

--json

--agent

to get structured output suitable for LLM consumption. Every command wraps its response in a standard envelope:

json

{
  "status": "success",
  "command": "search",
  "duration_ms": 245,
  "scope": { "user_id": "alice" },
  "count": 3,
  "error": null,
  "data": [
    { "id": "mem-abc", "memory": "User prefers dark mode", "score": 0.92 }
  ]
}

On error:

json

{
  "status": "error",
  "command": "search",
  "error": "Authentication failed. Your API key may be invalid or expired.",
  "data": null
}

The

--agent

flag is an alias for

--json

. Both write spinners and progress to stderr so stdout is always clean, parseable JSON.

使用

--json

或

--agent

参数获取适合LLM处理的结构化输出。每个命令的响应都会包裹在标准格式中：

json

{
  "status": "success",
  "command": "search",
  "duration_ms": 245,
  "scope": { "user_id": "alice" },
  "count": 3,
  "error": null,
  "data": [
    { "id": "mem-abc", "memory": "User prefers dark mode", "score": 0.92 }
  ]
}

错误时的输出：

json

{
  "status": "error",
  "command": "search",
  "error": "Authentication failed. Your API key may be invalid or expired.",
  "data": null
}

--agent

参数是

--json

的别名。两者都会将加载动画和进度信息写入stderr，因此stdout始终是干净、可解析的JSON。

Node and Python Parity

Node与Python版本一致性

Both the Node.js (

@mem0/cli

) and Python (

mem0-cli

) CLIs are implemented from the same specification (

cli-spec.json

). They share:

Identical command names, arguments, and flags
Identical output formats (text, json, table, quiet)
Identical entity ID resolution, graph tri-state, filter building
Identical error messages and exit codes

Choose whichever runtime you already have installed. The behavior is the same.

Node.js（

@mem0/cli

）和Python（

mem0-cli

）版本的CLI均基于同一规范（

cli-spec.json

）实现。它们具有以下共同点：

相同的命令名称、参数和标志
相同的输出格式（文本、json、表格、静默模式）
相同的实体ID解析、图三态、过滤器构建逻辑
相同的错误消息和退出码

选择你已安装的运行环境即可，两者行为完全一致。

Common Edge Cases

常见边缘情况

Async processing delay: After
```
mem0 add
```
, memories process asynchronously. Wait 2-3 seconds before searching for newly added content. Use
```
mem0 event list
```
to check processing status.
--all
vs
--entity
delete modes:
```
mem0 delete --all -u alice
```
deletes all memories for user alice.
```
mem0 delete --entity -u alice
```
deletes the entity itself AND all its memories (cascade). These are mutually exclusive modes.
Entity ID resolution: If you pass any explicit scope flag (e.g.
```
--user-id
```
), the CLI uses ONLY the explicit IDs and ignores config defaults. If no scope flags are given, all configured defaults apply.
Stdin detection: When no text argument is provided and input is piped (not a TTY), the CLI reads from stdin. Works with
```
add
```
,
```
search
```
, and
```
update
```
.

**异步处理延迟：**执行
```
mem0 add
```
后，内存会异步处理。等待2-3秒后再搜索新添加的内容。可使用
```
mem0 event list
```
检查处理状态。
--all
与
--entity
删除模式：
```
mem0 delete --all -u alice
```
会删除用户alice的所有内存。
```
mem0 delete --entity -u alice
```
会删除实体本身及其所有内存（级联删除）。这两种模式互斥。
**实体ID解析：**如果传递了任何显式范围标志（例如
```
--user-id
```
），CLI将仅使用显式ID，忽略配置默认值。如果未指定范围标志，则应用所有配置的默认值。
**标准输入检测：**当未提供文本参数且输入为管道传输（非TTY）时，CLI将从标准输入读取内容。适用于
```
add
```
、
```
search
```
和
```
update
```
命令。

References

参考资料

Load these on demand for deeper detail:

Topic	File
Command reference (all commands, flags, options, examples)	references/command-reference.md
Configuration (config file, env vars, precedence, init wizard)	references/configuration.md
Workflows (piping, scripting, CI/CD, agent mode recipes)	references/workflows.md

按需加载以下内容以获取更详细信息：

主题	文件
命令参考（所有命令、标志、选项、示例）	references/command-reference.md
配置（配置文件、环境变量、优先级、初始化向导）	references/configuration.md
工作流（管道、脚本、CI/CD、Agent模式方案）	references/workflows.md

Skill	When to use	Link
mem0	Python/TypeScript SDK, REST API, framework integrations	local / GitHub
mem0-vercel-ai-sdk	Vercel AI SDK provider with automatic memory	local / GitHub

技能	使用场景	链接
mem0	Python/TypeScript SDK、REST API、框架集成	local / GitHub
mem0-vercel-ai-sdk	带自动内存功能的Vercel AI SDK提供商	local / GitHub

mem0-cli

Original

Translation

Mem0 CLI

Mem0 CLI

Install

安装

Setup

设置

Quick Reference

快速参考

Add a memory

添加内存

Search memories

搜索内存

List all memories for a user

列出用户的所有内存

Get a specific memory

获取特定内存

Update a memory

更新内存

Delete a single memory

删除单个内存

Delete all memories for a user

删除用户的所有内存

Agent / JSON Mode

Agent / JSON模式

Node and Python Parity

Node与Python版本一致性

Common Edge Cases

常见边缘情况

References

参考资料

Related Mem0 Skills

相关Mem0技能