docs/build/snippets/python/code-samples/customization-memory-store-py.mdx

<CodeGroup>
    ```python Google
    from urllib.request import urlopen
    
    from deepagents import create_deep_agent
    from deepagents.backends import StoreBackend
    from deepagents.backends.utils import create_file_data
    from langgraph.store.memory import InMemoryStore
    
    with urlopen(
        "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
    ) as response:
        agents_md = response.read().decode("utf-8")
    
    # Create the store and add the file to it
    store = InMemoryStore()
    file_data = create_file_data(agents_md)
    store.put(
        namespace=("filesystem",),
        key="/AGENTS.md",
        value=file_data,
    )
    
    agent = create_deep_agent(
        model="google_genai:gemini-3.6-flash",
        backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
        store=store,
        memory=["/AGENTS.md"],
    )
    
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Please tell me what's in your memory files.",
                }
            ],
            "files": {"/AGENTS.md": create_file_data(agents_md)},
        },
        config={"configurable": {"thread_id": "12345"}},
    )
    ```

    ```python OpenAI
    from urllib.request import urlopen
    
    from deepagents import create_deep_agent
    from deepagents.backends import StoreBackend
    from deepagents.backends.utils import create_file_data
    from langgraph.store.memory import InMemoryStore
    
    with urlopen(
        "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
    ) as response:
        agents_md = response.read().decode("utf-8")
    
    # Create the store and add the file to it
    store = InMemoryStore()
    file_data = create_file_data(agents_md)
    store.put(
        namespace=("filesystem",),
        key="/AGENTS.md",
        value=file_data,
    )
    
    agent = create_deep_agent(
        model="openai:gpt-5.5",
        backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
        store=store,
        memory=["/AGENTS.md"],
    )
    
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Please tell me what's in your memory files.",
                }
            ],
            "files": {"/AGENTS.md": create_file_data(agents_md)},
        },
        config={"configurable": {"thread_id": "12345"}},
    )
    ```

    ```python Anthropic
    from urllib.request import urlopen
    
    from deepagents import create_deep_agent
    from deepagents.backends import StoreBackend
    from deepagents.backends.utils import create_file_data
    from langgraph.store.memory import InMemoryStore
    
    with urlopen(
        "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
    ) as response:
        agents_md = response.read().decode("utf-8")
    
    # Create the store and add the file to it
    store = InMemoryStore()
    file_data = create_file_data(agents_md)
    store.put(
        namespace=("filesystem",),
        key="/AGENTS.md",
        value=file_data,
    )
    
    agent = create_deep_agent(
        model="anthropic:claude-sonnet-4-6",
        backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
        store=store,
        memory=["/AGENTS.md"],
    )
    
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Please tell me what's in your memory files.",
                }
            ],
            "files": {"/AGENTS.md": create_file_data(agents_md)},
        },
        config={"configurable": {"thread_id": "12345"}},
    )
    ```

    ```python OpenRouter
    from urllib.request import urlopen
    
    from deepagents import create_deep_agent
    from deepagents.backends import StoreBackend
    from deepagents.backends.utils import create_file_data
    from langgraph.store.memory import InMemoryStore
    
    with urlopen(
        "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
    ) as response:
        agents_md = response.read().decode("utf-8")
    
    # Create the store and add the file to it
    store = InMemoryStore()
    file_data = create_file_data(agents_md)
    store.put(
        namespace=("filesystem",),
        key="/AGENTS.md",
        value=file_data,
    )
    
    agent = create_deep_agent(
        model="openrouter:z-ai/glm-5.2",
        backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
        store=store,
        memory=["/AGENTS.md"],
    )
    
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Please tell me what's in your memory files.",
                }
            ],
            "files": {"/AGENTS.md": create_file_data(agents_md)},
        },
        config={"configurable": {"thread_id": "12345"}},
    )
    ```

    ```python Fireworks
    from urllib.request import urlopen
    
    from deepagents import create_deep_agent
    from deepagents.backends import StoreBackend
    from deepagents.backends.utils import create_file_data
    from langgraph.store.memory import InMemoryStore
    
    with urlopen(
        "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
    ) as response:
        agents_md = response.read().decode("utf-8")
    
    # Create the store and add the file to it
    store = InMemoryStore()
    file_data = create_file_data(agents_md)
    store.put(
        namespace=("filesystem",),
        key="/AGENTS.md",
        value=file_data,
    )
    
    agent = create_deep_agent(
        model="fireworks:accounts/fireworks/models/glm-5p2",
        backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
        store=store,
        memory=["/AGENTS.md"],
    )
    
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Please tell me what's in your memory files.",
                }
            ],
            "files": {"/AGENTS.md": create_file_data(agents_md)},
        },
        config={"configurable": {"thread_id": "12345"}},
    )
    ```

    ```python Baseten
    from urllib.request import urlopen
    
    from deepagents import create_deep_agent
    from deepagents.backends import StoreBackend
    from deepagents.backends.utils import create_file_data
    from langgraph.store.memory import InMemoryStore
    
    with urlopen(
        "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
    ) as response:
        agents_md = response.read().decode("utf-8")
    
    # Create the store and add the file to it
    store = InMemoryStore()
    file_data = create_file_data(agents_md)
    store.put(
        namespace=("filesystem",),
        key="/AGENTS.md",
        value=file_data,
    )
    
    agent = create_deep_agent(
        model="baseten:zai-org/GLM-5.2",
        backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
        store=store,
        memory=["/AGENTS.md"],
    )
    
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Please tell me what's in your memory files.",
                }
            ],
            "files": {"/AGENTS.md": create_file_data(agents_md)},
        },
        config={"configurable": {"thread_id": "12345"}},
    )
    ```

    ```python Ollama
    from urllib.request import urlopen
    
    from deepagents import create_deep_agent
    from deepagents.backends import StoreBackend
    from deepagents.backends.utils import create_file_data
    from langgraph.store.memory import InMemoryStore
    
    with urlopen(
        "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
    ) as response:
        agents_md = response.read().decode("utf-8")
    
    # Create the store and add the file to it
    store = InMemoryStore()
    file_data = create_file_data(agents_md)
    store.put(
        namespace=("filesystem",),
        key="/AGENTS.md",
        value=file_data,
    )
    
    agent = create_deep_agent(
        model="ollama:north-mini-code-1.0",
        backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
        store=store,
        memory=["/AGENTS.md"],
    )
    
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Please tell me what's in your memory files.",
                }
            ],
            "files": {"/AGENTS.md": create_file_data(agents_md)},
        },
        config={"configurable": {"thread_id": "12345"}},
    )
    ```
</CodeGroup>