Files
mem0ai--mem0/docs/open-source/python-quickstart.mdx
T
wehub-resource-sync 555e282cc4
pi-agent-plugin checks / lint (push) Has been cancelled
pi-agent-plugin checks / test (20) (push) Has been cancelled
pi-agent-plugin checks / test (22) (push) Has been cancelled
pi-agent-plugin checks / build (push) Has been cancelled
TypeScript SDK CI / check_changes (push) Has been cancelled
TypeScript SDK CI / changelog_check (push) Has been cancelled
ci / changelog_check (push) Has been cancelled
ci / check_changes (push) Has been cancelled
ci / build_mem0 (3.10) (push) Has been cancelled
ci / build_mem0 (3.11) (push) Has been cancelled
ci / build_mem0 (3.12) (push) Has been cancelled
CLI Node CI / lint (push) Has been cancelled
CLI Node CI / test (20) (push) Has been cancelled
CLI Node CI / test (22) (push) Has been cancelled
CLI Node CI / build (push) Has been cancelled
CLI Python CI / lint (push) Has been cancelled
CLI Python CI / test (3.10) (push) Has been cancelled
CLI Python CI / test (3.11) (push) Has been cancelled
CLI Python CI / test (3.12) (push) Has been cancelled
CLI Python CI / build (push) Has been cancelled
openclaw checks / lint (push) Has been cancelled
openclaw checks / test (20) (push) Has been cancelled
openclaw checks / test (22) (push) Has been cancelled
openclaw checks / build (push) Has been cancelled
opencode-plugin checks / build (push) Has been cancelled
TypeScript SDK CI / build_ts_sdk (20) (push) Has been cancelled
TypeScript SDK CI / build_ts_sdk (22) (push) Has been cancelled
TypeScript SDK CI / integration_ts_sdk (20) (push) Has been cancelled
TypeScript SDK CI / integration_ts_sdk (22) (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:03:45 +08:00

109 lines
2.4 KiB
Plaintext

---
title: Python SDK Quickstart
description: "Install the Mem0 Python SDK, configure your environment, and store your first memory in under five minutes."
icon: "snake"
---
Get started with Mem0's Python SDK in under 5 minutes. This guide shows you how to install Mem0 and store your first memory.
## Prerequisites
- Python 3.10 or higher
- OpenAI API key ([Get one here](https://platform.openai.com/api-keys))
Set your OpenAI API key:
```bash
export OPENAI_API_KEY="your-openai-api-key"
```
<Note>
Uses OpenAI by default. Want to use Ollama, Anthropic, or local models? See [Configuration](/open-source/configuration).
</Note>
## Installation
<Steps>
<Step title="Install via pip">
```bash
pip install mem0ai
```
</Step>
<Step title="Initialize Memory">
```python
from mem0 import Memory
m = Memory()
````
</Step>
<Step title="Add a memory">
```python
messages = [
{"role": "user", "content": "Hi, I'm Alex. I love basketball and gaming."},
{"role": "assistant", "content": "Hey Alex! I'll remember your interests."}
]
m.add(messages, user_id="alex")
````
</Step>
<Step title="Search memories">
```python
results = m.search("What do you know about me?", filters={"user_id": "alex"})
print(results)
```
**Output:**
```json
{
"results": [
{
"id": "mem_123abc",
"memory": "Name is Alex. Enjoys basketball and gaming.",
"user_id": "alex",
"categories": ["personal_info"],
"created_at": "2025-10-22T04:40:22.864647-07:00",
"score": 0.89
}
]
}
```
</Step>
</Steps>
<Snippet file="star-on-github.mdx" />
<Note>
By default `Memory()` wires up:
- OpenAI `gpt-5-mini` for fact extraction and updates
- OpenAI `text-embedding-3-small` embeddings (1536 dimensions)
- Qdrant vector store with on-disk data at `/tmp/qdrant`
- SQLite history at `~/.mem0/history.db`
- No reranker (add one in the config when you need it)
</Note>
## What's next?
<CardGroup cols={3}>
<Card title="Memory operations" icon="database" href="/core-concepts/memory-operations/add">
Search, update, and manage memories with the full CRUD API.
</Card>
<Card title="Configure for production" icon="sliders" href="/open-source/configuration">
Swap in your own LLM, embedder, and vector store.
</Card>
<Card title="Add to your framework" icon="plug" href="/integrations">
Wire Mem0 into LangChain, CrewAI, LangGraph, and 20+ more.
</Card>
</CardGroup>
If you have any questions, please feel free to reach out:
<Snippet file="get-help.mdx" />