remember

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Mem0 Remember

Mem0 记忆存储

Store a fact or learning directly into mem0.

直接将事实或学习内容存入mem0。

Execution

执行步骤

Step 1: Extract the content

步骤1：提取内容

The user provides the content as an argument:

/mem0:remember <text>

If no text was provided, ask: "What should I remember?"

用户通过参数提供内容：

/mem0:remember <text>

如果未提供文本，询问：“我应该记住什么？”

Step 2: Classify the memory

步骤2：分类记忆

Based on the content, pick the best

metadata.type

Content signal	Type
"we decided...", "always use...", "never..."	`decision`
"X doesn't work because...", "don't try..."	`anti_pattern`
"I prefer...", "use X instead of Y"	`user_preference`
"the convention is...", "we always..."	`convention`
"learned that...", "figured out..."	`task_learning`
setup, env, tooling, config	`environmental`
anything else	`task_learning`

根据内容选择最合适的

metadata.type

：

内容信号	类型
“我们决定...”, “始终使用...”, “绝不...”	`decision`
“X无法工作是因为...”, “不要尝试...”	`anti_pattern`
“我偏好...”, “使用X而非Y”	`user_preference`
“惯例是...”, “我们总是...”	`convention`
“了解到...”, “弄清楚了...”	`task_learning`
设置、环境、工具、配置	`environmental`
其他任何内容	`task_learning`

Step 3: Store

步骤3：存储

Call

add_memory

with:

```
text="<the user's text>"
```
```
user_id=<active_user_id>
```
```
app_id=<active_project_id>
```

metadata={"type": "<classified_type>", "branch": "<active_branch>", "confidence": 1.0, "source": "remember_command"}

```
infer=False
```

infer=False

because the user stated the fact explicitly — no extraction needed.

confidence=1.0

because the user explicitly asked to store this.

调用

add_memory

接口，参数如下：

```
text="<用户输入的文本>"
```
```
user_id=<当前活跃用户ID>
```
```
app_id=<当前活跃项目ID>
```

metadata={"type": "<分类后的类型>", "branch": "<当前活跃分支>", "confidence": 1.0, "source": "remember_command"}

```
infer=False
```

设置

infer=False

是因为用户明确陈述了事实——无需额外提取。设置

confidence=1.0

是因为用户明确要求存储该内容。

Step 4: Confirm

步骤4：确认

The

add_memory

response returns

event_id

(not

memory_id

) because writes are async. Call

get_event_status(event_id=<event_id>)

once.

If status is
```
SUCCEEDED
```
: print the memory ID from the result.
If status is
```
PENDING
```
or
```
processing
```
: print with the event ID as fallback.

Remembered as <type>: "<content, first 80 chars>"
Memory ID: <id from event status>

Append

...

only if content was truncated (longer than 80 chars).

add_memory

接口返回

event_id

（而非

memory_id

），因为写入操作是异步的。调用一次

get_event_status(event_id=<event_id>)

：

如果状态为
```
SUCCEEDED
```
：打印结果中的记忆ID。
如果状态为
```
PENDING
```
或
```
processing
```
：使用事件ID作为备选进行打印。

已存储为<type>："<内容，前80个字符>"
记忆ID：<事件状态返回的ID>

仅当内容被截断（超过80字符）时才追加

...

。