> ## Documentation Index
> Fetch the complete documentation index at: https://docs.evermind.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Cloud Quickstart

> Get started with EverOS Cloud in under 5 minutes

## Prerequisites

* An [EverOS Cloud account](https://everos.evermind.ai/)
* An [API key](https://everos.evermind.ai/api-keys) — click "Create API Key", name it, and copy it securely
* Python 3.8 or higher

<Tip>
  Before getting your API key, [configure your Memory Space](https://everos.evermind.ai/memory-spaces) Scenario Mode. It influences how memories are extracted and consolidated. Learn more in the [Space Scenario Mode](/cloud/space-scenario-mode) guide.
</Tip>

<Steps>
  <Step title="Install the SDK">
    ```bash theme={null}
    pip install everos-cloud
    ```
  </Step>

  <Step title="Set your API key">
    ```python theme={null}
    from everos_cloud import EverOS

    client = EverOS(api_key="your_api_key")
    memories = client.v1.memories
    ```

    <Warning>
      Never commit API keys to version control. Use environment variables in production.
    </Warning>
  </Step>

  <Step title="Add memories">
    Store conversation messages into your Memory Space for processing and retrieval.

    ```python theme={null}
    import time

    now_ms = int(time.time() * 1000)

    response = memories.add(
        user_id="user_demo_001",
        session_id="session_gs_001",
        messages=[
            {
                "role": "user",
                "timestamp": now_ms,
                "content": "I like black Americano, no sugar, the stronger the better!",
            },
            {
                "role": "user",
                "timestamp": now_ms + 86_400_000,  # 1 day later
                "content": "Today I want to discuss the project progress.",
            },
        ],
    )
    print(f"status={response.data.status}  task_id={response.data.task_id}")

    # Flush to trigger immediate memory extraction
    memories.flush(user_id="user_demo_001", session_id="session_gs_001")
    ```
  </Step>

  <Step title="Retrieve memories">
    Fetch a user's stored memories directly by user ID.

    ```python theme={null}
    response = memories.get(
        filters={"user_id": "user_demo_001"},
        memory_type="episodic_memory",
    )

    episodes = response.data.episodes if response.data else []
    print(f"Fetched {len(episodes) if episodes else 0} memories")
    ```
  </Step>

  <Step title="Search memories">
    Find relevant memories using vector, keyword, or hybrid retrieval.

    ```python theme={null}
    response = memories.search(
        filters={"user_id": "user_demo_001"},
        query="coffee preference",
        method="vector",
        top_k=5,
    )

    episodes = response.data.episodes if response.data else []
    print(f"Found {len(episodes)} memories")
    ```
  </Step>
</Steps>

## What's Next?

<CardGroup cols={3}>
  <Card title="Core Concepts" icon="brain" href="/cloud/concepts/memory-lifecycle">
    Understand the memory lifecycle, memory types, and how EverOS processes your data.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Explore the full API with detailed parameter docs, request/response examples, and error codes.
  </Card>

  <Card title="Dashboard & Logs" icon="chart-line" href="https://everos.evermind.ai/dashboard">
    Monitor your quota usage, track API calls, and debug requests in the console.
  </Card>
</CardGroup>

<Note>
  **Need help?** Join our [community](https://discord.gg/geHdX4F24B).
</Note>