> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-rbacpe-1762465003-c2183e4.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Runtime

## Overview

LangChain's [`create_agent`](https://reference.langchain.com/python/langchain/agents/#langchain.agents.create_agent) runs on LangGraph's runtime under the hood.

LangGraph exposes a [`Runtime`](https://reference.langchain.com/python/langgraph/runtime/#langgraph.runtime.Runtime) object with the following information:

1. **Context**: static information like user id, db connections, or other dependencies for an agent invocation
2. **Store**: a [BaseStore](https://reference.langchain.com/python/langgraph/store/#langgraph.store.base.BaseStore) instance used for [long-term memory](/oss/python/langchain/long-term-memory)
3. **Stream writer**: an object used for streaming information via the `"custom"` stream mode

You can access the runtime information within [tools](#inside-tools) and [middleware](#inside-middleware).

## Access

When creating an agent with [`create_agent`](https://reference.langchain.com/python/langchain/agents/#langchain.agents.create_agent), you can specify a `context_schema` to define the structure of the `context` stored in the agent [`Runtime`](https://reference.langchain.com/python/langgraph/runtime/#langgraph.runtime.Runtime).

When invoking the agent, pass the `context` argument with the relevant configuration for the run:

```python theme={null}
from dataclasses import dataclass

from langchain.agents import create_agent


@dataclass
class Context:
    user_name: str

agent = create_agent(
    model="gpt-5-nano",
    tools=[...],
    context_schema=Context  # [!code highlight]
)

agent.invoke(
    {"messages": [{"role": "user", "content": "What's my name?"}]},
    context=Context(user_name="John Smith")  # [!code highlight]
)
```

### Inside tools

You can access the runtime information inside tools to:

* Access the context
* Read or write long-term memory
* Write to the [custom stream](/oss/python/langchain/streaming#custom-updates) (ex, tool progress / updates)

Use the `ToolRuntime` parameter to access the [`Runtime`](https://reference.langchain.com/python/langgraph/runtime/#langgraph.runtime.Runtime) object inside a tool.

```python theme={null}
from dataclasses import dataclass
from langchain.tools import tool, ToolRuntime  # [!code highlight]

@dataclass
class Context:
    user_id: str

@tool
def fetch_user_email_preferences(runtime: ToolRuntime[Context]) -> str:  # [!code highlight]
    """Fetch the user's email preferences from the store."""
    user_id = runtime.context.user_id  # [!code highlight]

    preferences: str = "The user prefers you to write a brief and polite email."
    if runtime.store:  # [!code highlight]
        if memory := runtime.store.get(("users",), user_id):  # [!code highlight]
            preferences = memory.value["preferences"]

    return preferences
```

### Inside middleware

You can access runtime information in middleware to create dynamic prompts, modify messages, or control agent behavior based on user context.

Use `request.runtime` to access the [`Runtime`](https://reference.langchain.com/python/langgraph/runtime/#langgraph.runtime.Runtime) object inside middleware decorators. The runtime object is available in the [`ModelRequest`](https://reference.langchain.com/python/langchain/middleware/#langchain.agents.middleware.ModelRequest) parameter passed to middleware functions.

```python theme={null}
from dataclasses import dataclass

from langchain.messages import AnyMessage
from langchain.agents import create_agent, AgentState
from langchain.agents.middleware import dynamic_prompt, ModelRequest, before_model, after_model
from langgraph.runtime import Runtime


@dataclass
class Context:
    user_name: str

# Dynamic prompts
@dynamic_prompt
def dynamic_system_prompt(request: ModelRequest) -> str:
    user_name = request.runtime.context.user_name  # [!code highlight]
    system_prompt = f"You are a helpful assistant. Address the user as {user_name}."
    return system_prompt

# Before model hook
@before_model
def log_before_model(state: AgentState, runtime: Runtime[Context]) -> dict | None:  # [!code highlight]
    print(f"Processing request for user: {runtime.context.user_name}")  # [!code highlight]
    return None

# After model hook
@after_model
def log_after_model(state: AgentState, runtime: Runtime[Context]) -> dict | None:  # [!code highlight]
    print(f"Completed request for user: {runtime.context.user_name}")  # [!code highlight]
    return None

agent = create_agent(
    model="gpt-5-nano",
    tools=[...],
    middleware=[dynamic_system_prompt, log_before_model, log_after_model],  # [!code highlight]
    context_schema=Context
)

agent.invoke(
    {"messages": [{"role": "user", "content": "What's my name?"}]},
    context=Context(user_name="John Smith")
)
```

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit the source of this page on GitHub.](https://github.com/langchain-ai/docs/edit/main/src/oss/langchain/runtime.mdx)
</Callout>

<Tip icon="terminal" iconType="regular">
  [Connect these docs programmatically](/use-these-docs) to Claude, VSCode, and more via MCP for    real-time answers.
</Tip>