---
title: Quickstart
description: 'Get started with Mem0 Platform in minutes'
---
## 1. Installation
Install the Mem0 Python package:
```bash
pip install mem0ai
```
## 2. API Key Setup
1. Sign in to [Mem0 Platform](https://app.mem0.ai/dashboard/api-keys)
2. Copy your API Key from the dashboard
## 3. Instantiate Client
```python
from mem0 import MemoryClient
client = MemoryClient(api_key="your-api-key")
```
## 4. Memory Operations
Mem0 provides a simple and customizable interface for performing CRUD operations on memory.
### 4.1 Create Memories
You can create long-term and short-term memories for your users, AI Agents, etc. Here are some examples:
#### Long-term memory for a user
```python Code
from mem0 import MemoryClient
client = MemoryClient(api_key="your-api-key")
messages = [
{"role": "user", "content": "Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts."},
{"role": "assistant", "content": "Hello Alex! I've noted that you're a vegetarian and have a nut allergy. I'll keep this in mind for any food-related recommendations or discussions."}
]
client.add(messages, user_id="alex")
```
#### Short-term memory for a user session
```python Code
from mem0 import MemoryClient
client = MemoryClient(api_key="your-api-key")
messages = [
{"role": "user", "content": "I'm planning a trip to Japan next month."},
{"role": "assistant", "content": "That's exciting, Alex! A trip to Japan next month sounds wonderful. Would you like some recommendations for vegetarian-friendly restaurants in Japan?"},
{"role": "user", "content": "Yes, please! Especially in Tokyo."},
{"role": "assistant", "content": "Great! I'll remember that you're interested in vegetarian restaurants in Tokyo for your upcoming trip. I'll prepare a list for you in our next interaction."}
]
client.add(messages, user_id="alex123", session_id="trip-planning-2024")
```
#### Long-term memory for agents
```python Code
from mem0 import MemoryClient
client = MemoryClient(api_key="your-api-key")
messages = [
{"role": "system", "content": "You are a personalized travel assistant. Remember user preferences and provide tailored recommendations."},
{"role": "assistant", "content": "Understood. I'll maintain personalized travel preferences for each user and provide customized recommendations based on their dietary restrictions, interests, and past interactions."}
]
client.add(messages, agent_id="travel-assistant")
```
You can monitor memory operations on the platform:
### 4.2 Search Relevant Memories
You can also get related memories for a given natural language question using our search method.
```python Code
query = "What do you know about me?"
client.search(query, user_id="alex")
```
```json Output
[
{
"id": "7f165f7e-b411-4afe-b7e5-35789b72c4a5",
"memory": "Name: Alex. Vegetarian. Allergic to nuts.",
"input": [
{
"role": "user",
"content": "Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts."
},
{
"role": "assistant",
"content": "Hello Alex! I've noted that you're a vegetarian and have a nut allergy. I'll keep this in mind for any food-related recommendations or discussions."
}
],
"user_id": "alex",
"hash": "9ee7e1455e84d1dab700ed8749aed75a",
"metadata": null,
"created_at": "2024-07-20T01:30:36.275141-07:00",
"updated_at": "2024-07-20T01:30:36.275172-07:00"
}
]
```
Similarly, you can search for agent memories by passing the `agent_id` argument.
```python Code
client.search("What are the learnings from previous runs?", agent_id="travel-assistant")
```
### 4.3 Get All Memories
Fetch all memories for a user, agent, or session using the get_all() method.
#### Get all memories of an AI Agent
```python Code
client.get_all(agent_id="travel-assistant")
```
```json Output
[
{
"id": "48677fae-16c4-4d57-9c27-f984f290722a",
"memory": "Will remember personalized travel preferences for each user.",
"input": [
{
"role": "system",
"content": "You are a personalized travel assistant. Remember user preferences and provide tailored recommendations."
},
{
"role": "assistant",
"content": "Understood. I'll maintain personalized travel preferences for each user and provide customized recommendations based on their dietary restrictions, interests, and past interactions."
}
],
"agent_id": "travel-assistant",
"hash": "644d5f40af13d0525305d8dfadc00fd1",
"metadata": null,
"created_at": "2024-07-20T01:25:22.122299-07:00",
"updated_at": "2024-07-20T01:25:22.122327-07:00"
}
]
```
#### Get all memories of user
```python Code
user_memories = client.get_all(user_id="alex")
```
```json Output
[
{
"id": "7f165f7e-b411-4afe-b7e5-35789b72c4a5",
"memory": "Name: Alex. Vegetarian. Allergic to nuts.",
"input": [
{
"role": "user",
"content": "Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts."
},
{
"role": "assistant",
"content": "Hello Alex! I've noted that you're a vegetarian and have a nut allergy. I'll keep this in mind for any food-related recommendations or discussions."
}
],
"user_id": "alex",
"hash": "9ee7e1455e84d1dab700ed8749aed75a",
"metadata": null,
"created_at": "2024-07-20T01:30:36.275141-07:00",
"updated_at": "2024-07-20T01:30:36.275172-07:00"
}
]
```
#### Get short-term memories for a session
```python Code
short_term_memories = client.get_all(user_id="alex123", session_id="trip-planning-2024")
```
```python Output
[
{
"id": "582bbe6d-506b-48c6-a4c6-5df3b1e63428",
"memory": "Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",
"input": [
{
"role": "user",
"content": "I'm planning a trip to Japan next month."
},
{
"role": "assistant",
"content": "That's exciting, Alex! A trip to Japan next month sounds wonderful. Would you like some recommendations for vegetarian-friendly restaurants in Japan?"
},
{
"role": "user",
"content": "Yes, please! Especially in Tokyo."
},
{
"role": "assistant",
"content": "Great! I'll remember that you're interested in vegetarian restaurants in Tokyo for your upcoming trip. I'll prepare a list for you in our next interaction."
}
],
"user_id": "alex123",
"hash": "d2088c936e259f2f5d2d75543d31401c",
"metadata": null,
"created_at": "2024-07-20T01:34:09.748379-07:00",
"updated_at": "2024-07-20T01:34:09.748391-07:00"
}
]
```
#### Get specific memory
```python Code
memory = client.get(memory_id="582bbe6d-506b-48c6-a4c6-5df3b1e63428")
```
```python Output
{
"id": "582bbe6d-506b-48c6-a4c6-5df3b1e63428",
"memory": "Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",
"input": [
{
"role": "user",
"content": "I'm planning a trip to Japan next month."
},
{
"role": "assistant",
"content": "That's exciting, Alex! A trip to Japan next month sounds wonderful. Would you like some recommendations for vegetarian-friendly restaurants in Japan?"
},
{
"role": "user",
"content": "Yes, please! Especially in Tokyo."
},
{
"role": "assistant",
"content": "Great! I'll remember that you're interested in vegetarian restaurants in Tokyo for your upcoming trip. I'll prepare a list for you in our next interaction."
}
],
"user_id": "alex123",
"hash": "d2088c936e259f2f5d2d75543d31401c",
"metadata": null,
"created_at": "2024-07-20T01:34:09.748379-07:00",
"updated_at": "2024-07-20T01:34:09.748391-07:00"
}
```
### 4.4 Memory History
Get history of how a memory has changed over time
```python Code
# Add some message to create history
messages = [{"role": "user", "content": "I recently tried chicken and I loved it. I'm thinking of trying more non-vegetarian dishes.."}]
client.add(messages, user_id="alex")
# Add second message to update history
messages.append({'role': 'user', 'content': 'I turned vegetarian now.'})
client.add(messages, user_id="alex")
# Get history of how memory changed over time
memory_id = ""
history = client.history(memory_id)
print(history)
```
```json Output
[
{
'id': '5a718c7e-7ed2-4c72-8c55-d7896dc61ca3',
'memory_id': 'c6c5da66-d851-4653-8a09-ec7b2c1c9cc9',
'input': [
{
'role': 'user',
'content': "I recently tried chicken and I loved it. I'm thinking of trying more non-vegetarian dishes.."
}
],
'old_memory': None,
'new_memory': 'Recently tried chicken and loved it. Interested in trying more non-vegetarian dishes.',
'event': 'ADD',
'metadata': None,
'created_at': '2024-07-20T02:13:35.842720-07:00',
'updated_at': '2024-07-20T02:13:35.818065-07:00'
},
{
'id': 'e52e2c73-4b97-4154-9844-aa44c6ee57f5',
'memory_id': 'c6c5da66-d851-4653-8a09-ec7b2c1c9cc9',
'input': [
{
'role': 'user',
'content': "I recently tried chicken and I loved it. I'm thinking of trying more non-vegetarian dishes.."
},
{
'role': 'user',
'content': 'I turned vegetarian now.'
}
],
'old_memory': 'Recently tried chicken and loved it. Interested in trying more non-vegetarian dishes.',
'new_memory': '',
'event': 'DELETE',
'metadata': None,
'created_at': '2024-07-20T02:13:38.070492-07:00',
'updated_at': '2024-07-20T02:13:38.060219-07:00'
}
]
```
### 4.5 Delete Memory
Delete specific memory:
```python Code
client.delete(memory_id)
```
```python Output
{'message': 'Memory deleted successfully!'}
```
Delete all memories of a user:
```python Code
client.delete_all(user_id="alex")
```
```python Output
{'message': 'Memories deleted successfully!'}
```
Fun fact: You can also delete the memory using the `add()` method by passing natural language command.
```python Code
client.add("Delete all of my food preferences", user_id="alex")
If you have any questions, please feel free to reach out to us using one of the following methods: