mem0

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Mem0 Platform Integration

Mem0 Platform集成

Mem0 is a managed memory layer for AI applications. It stores, retrieves, and manages user memories via API — no infrastructure to deploy.

Mem0是面向AI应用的托管式内存层，它通过API存储、检索和管理用户记忆——无需部署基础设施。

Step 1: Install and authenticate

步骤1：安装与认证

Python:

bash

pip install mem0ai
export MEM0_API_KEY="m0-your-api-key"

TypeScript/JavaScript:

bash

npm install mem0ai
export MEM0_API_KEY="m0-your-api-key"

Get an API key at: https://app.mem0.ai/dashboard/api-keys

Python：

bash

pip install mem0ai
export MEM0_API_KEY="m0-your-api-key"

TypeScript/JavaScript：

bash

npm install mem0ai
export MEM0_API_KEY="m0-your-api-key"

获取API密钥：https://app.mem0.ai/dashboard/api-keys

Step 2: Initialize the client

步骤2：初始化客户端

Python:

python

from mem0 import MemoryClient
client = MemoryClient(api_key="m0-xxx")

TypeScript:

typescript

import MemoryClient from 'mem0ai';
const client = new MemoryClient({ apiKey: 'm0-xxx' });

For async Python, use

AsyncMemoryClient

Python：

python

from mem0 import MemoryClient
client = MemoryClient(api_key="m0-xxx")

TypeScript：

typescript

import MemoryClient from 'mem0ai';
const client = new MemoryClient({ apiKey: 'm0-xxx' });

对于异步Python，使用

AsyncMemoryClient

。

Step 3: Core operations

步骤3：核心操作

Every Mem0 integration follows the same pattern: retrieve → generate → store.

所有Mem0集成都遵循相同的模式：检索 → 生成 → 存储。

Add memories

添加记忆

python

messages = [
    {"role": "user", "content": "I'm a vegetarian and allergic to nuts."},
    {"role": "assistant", "content": "Got it! I'll remember that."}
]
client.add(messages, user_id="alice")

python

messages = [
    {"role": "user", "content": "I'm a vegetarian and allergic to nuts."},
    {"role": "assistant", "content": "Got it! I'll remember that."}
]
client.add(messages, user_id="alice")

Search memories

搜索记忆

python

results = client.search("dietary preferences", user_id="alice")
for mem in results.get("results", []):
    print(mem["memory"])

python

results = client.search("dietary preferences", user_id="alice")
for mem in results.get("results", []):
    print(mem["memory"])

Get all memories

获取所有记忆

python

all_memories = client.get_all(user_id="alice")

python

all_memories = client.get_all(user_id="alice")

Update a memory

更新记忆

python

client.update("memory-uuid", text="Updated: vegetarian, nut allergy, prefers organic")

python

client.update("memory-uuid", text="Updated: vegetarian, nut allergy, prefers organic")

Delete a memory

删除记忆

python

client.delete("memory-uuid")
client.delete_all(user_id="alice")  # delete all for a user

python

client.delete("memory-uuid")
client.delete_all(user_id="alice")  # delete all for a user

Common integration pattern

常见集成模式

python

from mem0 import MemoryClient
from openai import OpenAI

mem0 = MemoryClient()
openai = OpenAI()

def chat(user_input: str, user_id: str) -> str:
    # 1. Retrieve relevant memories
    memories = mem0.search(user_input, user_id=user_id)
    context = "\n".join([m["memory"] for m in memories.get("results", [])])

    # 2. Generate response with memory context
    response = openai.chat.completions.create(
        model="gpt-4.1-nano-2025-04-14",
        messages=[
            {"role": "system", "content": f"User context:\n{context}"},
            {"role": "user", "content": user_input},
        ]
    )
    reply = response.choices[0].message.content

    # 3. Store interaction for future context
    mem0.add(
        [{"role": "user", "content": user_input}, {"role": "assistant", "content": reply}],
        user_id=user_id
    )
    return reply

python

from mem0 import MemoryClient
from openai import OpenAI

mem0 = MemoryClient()
openai = OpenAI()

def chat(user_input: str, user_id: str) -> str:
    # 1. Retrieve relevant memories
    memories = mem0.search(user_input, user_id=user_id)
    context = "\n".join([m["memory"] for m in memories.get("results", [])])

    # 2. Generate response with memory context
    response = openai.chat.completions.create(
        model="gpt-4.1-nano-2025-04-14",
        messages=[
            {"role": "system", "content": f"User context:\n{context}"},
            {"role": "user", "content": user_input},
        ]
    )
    reply = response.choices[0].message.content

    # 3. Store interaction for future context
    mem0.add(
        [{"role": "user", "content": user_input}, {"role": "assistant", "content": reply}],
        user_id=user_id
    )
    return reply

Common edge cases

常见边缘情况

Search returns empty: Memories process asynchronously. Wait 2-3s after
```
add()
```
before searching. Also verify
```
user_id
```
matches exactly (case-sensitive).
AND filter with user_id + agent_id returns empty: Entities are stored separately. Use
```
OR
```
instead, or query separately.
Duplicate memories: Don't mix
```
infer=True
```
(default) and
```
infer=False
```
for the same data. Stick to one mode.

Wrong import: Always use

from mem0 import MemoryClient

(or

AsyncMemoryClient

for async). Do not use

from mem0 import Memory

Immutable memories: Cannot be updated or deleted once created. Use
```
client.history(memory_id)
```
to track changes over time.

搜索返回空结果： 记忆处理是异步的。在调用
```
add()
```
后等待2-3秒再进行搜索。同时请确认
```
user_id
```
完全匹配（区分大小写）。
使用user_id + agent_id的AND过滤器返回空结果： 实体是分开存储的。改用OR过滤器，或分别查询。
重复记忆： 不要对同一数据混合使用
```
infer=True
```
（默认值）和
```
infer=False
```
。请坚持使用一种模式。
错误的导入方式： 请始终使用
```
from mem0 import MemoryClient
```
（异步场景使用
```
AsyncMemoryClient
```
）。不要使用
```
from mem0 import Memory
```
。
不可变记忆： 记忆创建后无法更新或删除。使用
```
client.history(memory_id)
```
跟踪随时间的变更。

Live documentation search

在线文档搜索

For the latest docs beyond what's in the references, use the doc search tool:

bash

python scripts/mem0_doc_search.py --query "topic"
python scripts/mem0_doc_search.py --page "/platform/features/graph-memory"
python scripts/mem0_doc_search.py --index

No API key needed — searches docs.mem0.ai directly.

如需获取参考内容之外的最新文档，可使用文档搜索工具：

bash

python scripts/mem0_doc_search.py --query "topic"
python scripts/mem0_doc_search.py --page "/platform/features/graph-memory"
python scripts/mem0_doc_search.py --index

无需API密钥——直接搜索docs.mem0.ai。

References

参考资料

Load these on demand for deeper detail:

Topic	File
Quickstart (Python, TS, cURL)	references/quickstart.md
SDK guide (all methods, both languages)	references/sdk-guide.md
API reference (endpoints, filters, object schema)	references/api-reference.md
Architecture (pipeline, lifecycle, scoping, performance)	references/architecture.md
Platform features (retrieval, graph, categories, MCP, etc.)	references/features.md
Framework integrations (LangChain, CrewAI, Vercel AI, etc.)	references/integration-patterns.md
Use cases & examples (real-world patterns with code)	references/use-cases.md

按需加载以下内容以获取更详细的信息：

主题	文件
快速入门（Python、TS、cURL）	references/quickstart.md
SDK指南（所有方法、两种语言）	references/sdk-guide.md
API参考（端点、过滤器、对象架构）	references/api-reference.md
架构（流水线、生命周期、作用域、性能）	references/architecture.md
平台功能（检索、图谱、分类、MCP等）	references/features.md
框架集成（LangChain、CrewAI、Vercel AI等）	references/integration-patterns.md
用例与示例（带代码的真实场景模式）	references/use-cases.md